WO2016123657A1 - Computer implemented frameworks and methodologies configured to enable generation of a synthetic profit and loss report based on business data, and loan management based on including risk-based loan construction and pricing and/or pricing based on data analysis of default risk and loss given default parameters - Google Patents

Abstract

Described herein are technologies including frameworks and methodologies for enabling centralised management of a loan determination process. Embodiments of the invention have been particularly developed for enabling services in relation to small business credit assessment. For example, certain embodiments include generation of a synthetic profit and loss data file, which is generated via inventive and non-generic application of information management and processing techniques. In particular, the technology leverages database of the "average" profit & loss for a given business type and size, identifies a set of average data relevant to a given loan applicant, and customises that set of data using obtainable data specific to the applicant. The resulting data is a combination of industry standard data and customer specific data, with the degree of confidence in the output determined by the degree to which standardised inputs have been replaced.

Description

COMPUTER IMPLEMENTED FRAMEWORKS AND METHODOLOGIES CONFIGURED TO ENABLE GENERATION OF A SYNTHETIC PROFIT AND LOSS REPORT BASED ON BUSINESS DATA, AND LOAN MANAGEMENT BASED ON INCLUDING RISK-BASED LOAN CONSTRUCTION AND PRICING AND/OR PRICING BASED ON DATA ANALYSIS OF DEFAULT RISK AND LOSS GIVEN DEFAULT PARAMETERS

FIELD OF THE INVENTION

[0001] The present invention relates to computer implemented frameworks and methodologies for enabling centralised management of a loan determination process. For example, these provide technical/technological means for solving problems associated with automated loan decisioning in the online space. Embodiments of the invention have been particularly developed for enabling services in relation to small business credit assessment. For example, certain embodiments include generation of a synthetic profit and loss data file, which leverages database of the "average" profit & loss for a given business type and size, identifies a set of average data relevant to a given loan applicant, and customises that set of data using obtainable data specific to the applicant. The resulting data is a combination of industry standard data and customer specific data, with the degree of confidence in the output determined by the degree to which standardised inputs have been replaced. While some embodiments will be described herein with particular reference to that application, it will be appreciated that the invention is not limited to such a field of use, and is applicable in broader contexts.

BACKGROUND

[0002] Any discussion of the background art throughout the specification should in no way be considered as an admission that such art is widely known or forms part of common general knowledge in the field. [0003] Credit assessment, for example in the context of making determinations in relation to loans to SMEs, is traditionally a time-consuming manual process. Challenges stem from factors including the likes of:

• Information Asymmetry: stemming from limited public information about financial performance of small business, and difficulty verifying much of the information provided from business owner.

• Low Quality Information: financial accounts are often managed down for tax purposes and often blend personal and business expenses; it is common for "profitable" SMEs to be reporting tax loss or breakeven.

• Susceptibility to business cycle: SMEs are more susceptible to business cycle effects than larger business (lower cash buffer, limited access to sources of emergency cash, more adversely impacted by payment term extensions in economic downturn).

• High Processing Costs: Often it is more time consuming to assess a $50,000 loan, than a $2,000,000 loan (for example due to one or more of the preceding points).

[0004] There is a need in the art for improved approaches to assessing SME loans, and more particularly a need to make more effective use of computer technology in the general field of loan processing. In that regard, use of known generic computing and software technologies in obvious ways have failed to deliver suitable useful results in the context of the loan processing field.

SUM MARY OF THE INVENTION

[0005] It is an object of the present invention to overcome or ameliorate at least one of the disadvantages of the prior art, or to provide a useful alternative.

[0006] One embodiment provides a computer implemented method for enabling generation of a synthetic profit and loss data file, the method including:

[0007] identifying a target business; [0008] determining an industry parameter for the target business;

[0009] determining a business size parameter for the target business;

[0010] accessing a database that maintains baseline P&L data for a plurality of businesses, categorised by business size and industry;

[0011] extracting from the database a set of P&L data from the database based upon the determined industry parameter and determined business size parameter;

[0012] populating a P&L data file with data values for individual line items based the extracted set of P&L data;

[0013] extracting, from data sources accessible via the Internet, either or both of:

[0014] transactional data for the target business from a source of online banking data;

[0015] accounting record data for the target business from an accounting software platform used by the target business; and

[0016] for each of at least a subset of the line items, applying a respective data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data.

[0017] One embodiment provides a computer implemented method including defining a score representative of the proportion of the line items for which the populated value is replaced.

[0018] One embodiment provides a computer implemented method wherein the baseline P&L data represents a predefined observed average for businesses of a given industry and business size, and wherein the method includes providing an output representative of performance of the target business relative to the predefined observed average [0019] One embodiment provides a computer implemented method for enabling generation of a synthetic profit and loss data file, the method including:

[0020] identifying a target business;

[0021] selecting, from a set of available P&L templates, a specific P&L template for the target business;

[0022] populating the P&L template with data values for individual line items based on data uploaded by the target business;

[0023] extracting transactional data for the target business from a source of online banking data;

[0024] extracting accounting record data for the target business from an accounting software platform used by the target business; and

[0025] for each of at least a subset of the line items, applying a respective data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data.

[0026] One embodiment provides a computer implemented method for enabling processing of loan applications, constructing loan parameters and setting of loan pricing (risk based loan construction and pricing) the method including:

[0027] providing an interface that enables users of respective client terminals to upload respective loan application data sets;

[0028] for a given uploaded loan application data set:

[0029] a method for collecting information on a loan application, applying a protocol to determine the risk of the loan and then determining a loan structure, terms and price

[0030] (i) applying a first assessment protocol in respect of the application data set, wherein the first assessment protocol is an automated process performed based upon data contained in the application data set, and data obtained from one or more third party sources based upon data contained in the application data set;

[0031] (ii) determining whether an output of the first assessment protocol meets first predefined requirements;

[0032] (iii) in the case that the predefined requirements are met, applying a first loan parameters algorithm thereby to define a loan offer, including loan terms and pricing, in respect of the loan application data set;

[0033] (iv) in the case that the predefined requirements are not met, progressing the loan application date set to a second assessment protocol;

[0034] (v) implementing the second assessment protocol in respect of the loan application data set, wherein implementing the second assessment protocol includes:

[0035] (a) defining a set of manual tasks;

[0036] (b) providing the defined set of manual tasks to a task management module, which is configured to coordinate assignment of the tasks across a plurality of distributed users;

[0037] (c) receiving quantitative data responses in respect of each of the defined set of manual tasks following manual completion of those tasks;

[0038] (vi) determining a combined output of the first and second assessment protocols;

[0039] (vii) determining whether the combined output meets second predefined requirements;

[0040] (viii) in the case that the second predefined requirements are met, applying a second loan parameters algorithm thereby to define a loan offer in respect of the loan application data set. [0041] providing an interface configured to communicate to the users data representing outcomes of the first and/or second assessment protocols.

[0042] One embodiment provides a computer implemented method including, based on at least one of the first and second assessment protocols, defining one or more risk parameters for the loan application data set, and based on those defined one or more risk parameters, defining a loan offer having a set of loan rules.

[0043] One embodiment provides a computer implemented method wherein the loan rules are defined responsive to the defined one or more risk parameters, and include one or more of: a repayment schedule; rules for graduated release of loan funds; and loan interest rates.

[0044] One embodiment provides a computer implemented method wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: business accounting data generated by the user via an accounting software package.

[0045] One embodiment provides a computer implemented method wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: transaction data extracted from electronic banking records.

[0046] One embodiment provides a computer implemented method wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: credit record data from one or more providers of credit record data.

[0047] One embodiment provides a computer implemented method wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: business information verification data from an independent business data registry.

[0048] One embodiment provides a computer implemented method for enabling determination of a credit score for a business, the method including: [0049] applying a first algorithm thereby to determine a default probability score representative of risk of default in respect of a loan application;

[0050] applying a second algorithm thereby to determine a loss given default score representative of estimated loss in event of default in respect of the loan application; and

[0051] applying a third algorithm which uses input including the determined default probability score and determined loss given default score thereby to define a hybrid expected loss score and expected loss value, the later which is compared to expected return in order to make a lending decision.

[0052] One embodiment provides a computer implemented method wherein the loss given default score is inversely related to attributable to the business' owner(s) and/or di recto r(s).

[0053] One embodiment provides a computer implemented method for wherein the second algorithm uses inputs including one or more of the following:

[0054] a number of directors;

[0055] for each director, a number of properties owned;

[0056] for each property, whether the property is owned or rented;

[0057] for each property, an estimated value for the property;

[0058] for each property, a holding time for the property;

[0059] for each property, an estimated annual growth rate for the property;

[0060] for each property, an approximated equity proportion and/or value;

[0061] for each property, a loan-to-value ratio for the property.

[0062] One embodiment provides a computer implemented method wherein the second algorithm includes: [0063] determining a director score;

[0064] determining weights for director owned properties; and [0065] determining weights for director rented properties.

[0066] One embodiment provides a computer implemented method wherein determination of a director score includes determining a number of directors, and identifying relationships between directors.

[0067] One embodiment provides a computer implemented method 1 wherein the applying the second algorithm includes accessing one or more external information sources thereby to obtain details of one or more properties identified in the loan application.

[0068] One embodiment provides a computer implemented method for enabling determination of a credit score for a business, the method including:

[0069] applying an algorithm thereby to determine a Loss Given Default score representative of estimated loss in event of default of a loan sum respect of the loan application;

[0070] wherein the Loss Given Default score is inversely related to equity in property attributable to the business' owner(s) and/or director(s); and

[0071] wherein the algorithm uses inputs including one or more of the following:

[0072] a number of directors;

[0073] for each director, a number of properties owned;

[0074] for each property, whether the property is owned or rented;

[0075] for each property, an estimated value for the property;

[0076] for each property, a holding time for the property; [0077] for each property, an estimated annual growth rate for the property;

[0078] for each property, an approximated equity proportion and/or value;

[0079] for each property, a loan-to-value ratio for the property

[0080] a sector within which the borrowing entity operates;

[0081] a amount of estimated debt held by the business;

[0082] a amount of estimated debt held by each of the directors.

[0083] One embodiment provides a computer implemented method wherein the algorithm includes:

[0084] determining a director score;

[0085] determining weights for director owned properties; and [0086] determining weights for director rented properties.

[0087] One embodiment provides a computer implemented method wherein determination of a director score includes determining a number of directors, and identifying relationships between directors.

[0088] One embodiment provides a computer implemented method wherein the applying the algorithm includes accessing one or more external information sources thereby to obtain details of one or more properties identified in the loan application.

[0089] One embodiment provides a computer program product for performing a method as described herein.

[0090] One embodiment provides a non-transitive carrier medium for carrying computer executable code that, when executed on a processor, causes the processor to perform a method as described herein. [0091] One embodiment provides a system configured for performing a method as described herein.

[0092] Reference throughout this specification to "one embodiment", "some embodiments" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases "in one embodiment", "in some embodiments" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but may. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner, as would be apparent to one of ordinary skill in the art from this disclosure, in one or more embodiments.

[0093] As used herein, unless otherwise specified the use of the ordinal adjectives "first", "second", "third", etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.

[0094] In the claims below and the description herein, any one of the terms comprising, comprised of or which comprises is an open term that means including at least the elements/features that follow, but not excluding others. Thus, the term comprising, when used in the claims, should not be interpreted as being limitative to the means or elements or steps listed thereafter. For example, the scope of the expression a device comprising A and B should not be limited to devices consisting only of elements A and B. Any one of the terms including or which includes or that includes as used herein is also an open term that also means including at least the elements/features that follow the term, but not excluding others. Thus, including is synonymous with and means comprising.

[0095] As used herein, the term "exemplary" is used in the sense of providing examples, as opposed to indicating quality. That is, an "exemplary embodiment" is an embodiment provided as an example, as opposed to necessarily being an embodiment of exemplary quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Embodiments of the invention will now be described, by way of example only, with reference to the accompanying drawings in which:

[0097] FIG. 1 schematically illustrates a framework according to one embodiment.

[0098] FIG. 2A illustrates a method according to one embodiment. [0099] FIG. 2B illustrates a method according to one embodiment. [00100] FIG. 2C illustrates a method according to one embodiment.

[00101] FIG. 3 illustrates a client-server framework leveraged by various embodiments.

[00102] FIG. 4A to FIG. 4F show information renderings according to various embodiments.

DETAILED DESCRIPTION

[00103] The present invention relates to frameworks and methodologies for enabling centralised management of a loan determination process. Embodiments of the invention have been particularly developed for enabling services in relation to small business credit assessment. For example, certain embodiments include generation of a synthetic profit and loss data file, which is generated via inventive and non-generic application of information management and processing techniques. In particular, the technology leverages database of the "average" profit & loss for a given business type and size, identifies a set of average data relevant to a given loan applicant, and customises that set of data using obtainable data specific to the applicant. The resulting data is a combination of industry standard data and customer specific data, with the degree of confidence in the output determined by the degree to which standardised inputs have been replaced. While some embodiments will be described herein with particular reference to that application, it will be appreciated that the invention is not limited to such a field of use, and is applicable in broader contexts. Overview

[00104] Various embodiments provide computer implemented frameworks that are configurable to enable processing of loans for SMEs based on various loan approval algorithms. Although some exemplary loan approval algorithms are described further below, it will be appreciated that the described frameworks are able to operate across a range of subjectively defined loan approval algorithms in an efficient manner, given the way in which computer technologies have been adapted to provide increased efficiencies in the field of loan approvals.

[00105] In overview, one framework is configured to provide an interface that enables users of respective client terminals to upload respective loan application data sets. For example, this may occur via a web-based platform, whereby users load respective user interfaces from remotely hosted data using web browser applications. This optionally guides each user through an interactive process, whereby data is supplied and/or documents uploaded thereby to define a loan application data set.

[00106] It will be appreciated that automating aspects of loan applications involved technological challenges. For example, traditionally loan decisions are made based on a combination of objective and subjective factors, using a range of available information. A trend towards to utilisation of objective factors is of assistance in the context of process automation, but inherently increases the chances of unnecessarily rejecting loan applications. Embodiments described below include technology that is implemented to enable new and inventive applications of computer technology, in a non-generic manner, thereby to overcome technical hurdles in the loan processing space (particularly the automated loan processing space).

[00107] In the illustrated embodiment, each uploaded loan application data set is handled using a two-phase assessment process, which includes a preliminary automated phase, and a secondary manual phase. The framework is configured, in this regard, to increase efficiencies in processes that may require manual intervention. In particular, the preliminary automated phase applies a first assessment protocol in respect of the application data set, wherein the first assessment protocol is an automated process performed based upon data contained in the application data set, and data obtained from one or more third party sources based upon data contained in the application data set. This results in a first output, which is assessed based on predefined requirements. If those requirements are met, a loan parameters algorithm is used to generate a loan offer. If those requirements are not met, the process moves into the second phase, where manual intervention is required. This is, in embodiments described herein, achieved via a second assessment protocol.

[00108] This second assessment protocol includes: (a) defining a set of manual tasks; (b) providing the defined set of manual tasks to a task management module, which is configured to coordinate assignment of the tasks across a plurality of distributed users; and (c) receiving quantitative data responses in respect of each of the defined set of manual tasks following manual completion of those tasks. In some cases, where there are multiple task performers, workloads are split between the task performers based on task type, as opposed to on an application-by-application basis. In this manner, each individual task performer may perform the same task (or a similar set of tasks) repeatedly for a plurality of loan applications, hence greatly increasing processing efficiency (and optimally reducing training and/or minimum skill requisites).

[00109] A combined output of the first and second assessment protocols is processed to determine whether predefined requirements are met. Assuming those are met, a second loan parameters algorithm is applied thereby to define a loan offer in respect of the loan application data set.

[00110] It should be appreciated that, whilst some embodiments are described by reference to a hybrid automated/manual process, various technologies described herein provide wholly automated sub-processes which are equally relevant to such hybrid processes and other processes.

Exemplary Framework

[0011 1] FIG. 1 illustrates a framework according to one embodiment. This framework centres upon a loan application processing server 100. Although server 100 is illustrated as a single component, it should be appreciated that in practice it may be defined by a plurality of discrete computing components, which may in some cases be distributed in location. Server 100 is described by reference to a plurality of functional components, which are provided collectively by a suite of software applications and hardware devices. For the present disclosure the functional components are separated and described by reference to their function for the purposes of efficient explanation. [00112] Server 100 interacts with a plurality of applicant terminals 140, including an exemplary applicant terminal 140'. At a functional level, these are defined by terminals operated by loan applicants (for example representatives of SMEs applying for loan financing via a provider associated with server 100), and the terminals need not have any particular hardware-level characteristics defining them as "applicant terminals".

[00113] The applicant terminals may include a wide range of computing devices, including devices that communicate with server 100 via any one or more of: a proprietary software based arrangement; a web-browser based arrangement; and other communications arrangements. Terminal 140' renders an applicant user interface on a screen 141 , thereby to enable a user to review information provided for the purposes of interaction with server 100, and enable submission of information to server 100 (which includes applicant interface modules 104 thereby to facilitate interaction with terminals 140). Terminal 140' additionally includes a processor 142, which is configured to execute software instructions maintained on a memory module 143, thereby to perform computer implemented methods defined by executed code (software instructions). A communications module 144 enables communication between terminal 140' and server 100 (for example via a WiFi module, Internet router, and so on).

[00114] Based upon interaction between terminals 140 and server 100 (via modules 104), server 100 is configured to maintain a repository of applicant data 102. This includes identifying information for each loan applicant business, including contact details, logon details, information required to access third party information sources pertaining to the applicant (for example account IDs and passwords for sources such as electronic banking, and accounting platforms, and the like), and other such information. Server 100 also maintains a repository of application data, which contains information defining loan application data sets. It will be appreciated that each applicant may be associated with a one or more loan application data sets.

[00115] An assessment rules engine is configured to process loan application data sets in application data 103. In general terms, this includes progressing through various automated processes, including data processing, application management, and so on. Some more detailed examples are provided further below. Rules upon which the rules engine operates are able to be modified over time, thereby to achieve additional optimisation in the loan processing process (for example by modifying algorithms, weightings in algorithms, adding additional automated and/or manual tasks, and so on). [00116] Rules engine 105 causes an external systems integration module 108 to obtain, from a plurality of external data sources, additional data for each new loan application. This obtained data is processed (for example via normalisation and/or other procedures) and stored with the relevant loan application data set in application data 103.

[00117] In the illustrated example, the external systems include applicant accounting software platforms 138, and other external data provider platforms 139.

[00118] In relation to applicant accounting software platforms 138, a loan applicant provides to server 100 identifying information thereby to enable server 100 to access their accounting records. For example, this may include identifying a software provider, and account credentials. In some embodiments the accounting software platforms include cloud-hosted platforms, whereby accounting records are hosted in the cloud, and hence able to be conveniently accessed by other computer systems (for example using an API or the like). In cases where local desktop accounting programs are used, a local software module may be installed (for example a plugin or the like thereby to provide server 100 with access to the local software program).

[00119] In various embodiments, the following information is collected from external sources:

• Business credit report.

• Credit reports on all business directors.

• Profit and loss data, balance sheet data and other information from accounting software (for example cloud hosted accounting software).

• Transaction data from business transaction account (optionally via 3^rd party information provider).

• Government register data (for example ASIC for Australia).

• Personal Property Security Register data (or non-Australian equivalent).

• Transaction data from online sales platforms (such as eBay). [00120] Server 100 is configured to implement a two-phase loan application processing methodology. The first phase is an automated phase performed by automated assessment module 107. This uses quantitative data in application data 103 thereby to drive a loan parameters algorithm, thereby to define loan parameters in respect of individual loan application data sets in the case that threshold automatic approval conditions are satisfied.

[00121] Where those conditions are not satisfied for a given loan application, rules engine 105 is configured to progress that application to be handled by a task management module 109. Module 109 is responsible for coordinating the second of the two phases, which is a phase involving a plurality of manual tasks. Task management module defines those tasks, and places them in one or more queues for completion by human assessors (task performers).

[00122] Server 100 interacts with a plurality of assessor terminals 140, including an exemplary assessor terminal 130'. The assessor terminals are terminals operated by "assessors", being human users utilised to perform manual tasks associated with loan processing by server 100.

[00123] The assessor terminals may include a wide range of computing devices, including devices that communicate with server 100 via any one or more of: a proprietary software based arrangement; a web-browser based arrangement; and other communications arrangements. Terminal 130' renders an assessor user interface on a screen 131 , thereby to enable a user to review information provided for the purposes of interaction with server 100, and enable submission of information to server 100 (which includes assessor interface modules 104 thereby to facilitate interaction with terminals 140). Terminal 130' additionally includes a processor 132, which is configured to execute software instructions maintained on a memory module 133, thereby to perform computer implemented methods defined by executed code (software instructions). A communications module 134 enables communication between terminal 140' and server 100 (for example via a WiFi module, Internet router, and so on). In some cases one or more of terminals 130 operate on a common LAN to server 100 (or in some cases on a common l_AN to one or more components of server 100).

[00124] In a preferred embodiment, an assessor user accesses the assessor user interface, and is provided with a list of tasks to complete. The list of tasks is set by module 109, and may be specific to the individual assessor user (for example based on the user's training, based on workload balancing between multiple users, and so on). Preferably, a given assessor user "assessor A" is allocated a plurality of "type A" tasks relating to a number of different loan applications, whereas "assessor B" is allocated a plurality of "type B" tasks relating to a number of different loan applications (with overlap between the applications with which assessors A and B assist).

[00125] Manual tasks may include review based on:

• Applicant social feeds (Facebook, eBay store, Urbanspoon and Tripadvisor).

• Manual review and image capture of Google Streetview for directors' primary residence and main business address, along with, for example, OnTheHouse value of directors' houses and Realestate.com.au last sold date for properties.

[00126] A P&L (profit and loss) synthesizer module 106 is configured to generate a synthetic profit and loss data file in respect of each loan application. This module is configured to implement technical solution to overcome challenges associated with obtaining high quality objectively processable information in the context of an automated (or partially automated) loan determination process. This is discussed in additional detail further below.

[00127] Traditionally, banks and other financial institutions have set the pricing and terms of small business loans upfront and apply a "pass/"fail" test against predefined credit criteria in making a loan decision.

[00128] These credit criteria have historically been heavily weighted to the collateral that is offered by the small business as security for the loan with limited focus on cashflow and other financial aspects of the business. This is due, in part, to the complexity and time involved in processing and assessing cashflow data from small businesses (there is greater information asymmetry between borrower and lender in the small business sector than in other market segments). In recent years, with the advances in technology, some lenders have begun to leverage online platforms to automate loan credit decisioning via the development of sophisticated in-house credit engines. The result is a fast and automated online credit decision for small business. [00129] However, these new automated credit engines still operate a 'pass/fail' test against predefined credit criteria. This approach results in a high percentage of loan application rejections. A solution to this issue is the development of a dynamic credit model that does not have predefined credit criteria but instead analyses the applicant's data first in order to determine a loan structure, loan duration, loan amount and loan terms and interest that provides the lender with an adequate return for the risk of the loan, for every loan. Theoretically, this approach can facilitate a 100% approval rate on loan applications, with the lenders credit risk mitigated via the construction of the price and terms of the loan.

Exemplary Loan Application Management Process

[00130] FIG. 2A illustrates an exemplary loan application management process. This includes a method 200, which is performed at an applicant terminal, and a method 201 , performed by server 100.

[00131] Functional block 201 represents a process including a registration phase, whereby a user registers as an applicant on behalf of a SME. This includes providing various aspects of applicant data 102. Then, at 202, the user inputs application data specific to a particular application. This data, when uploaded, triggers method 210.

[00132] Functional block 21 1 represents a process including receiving application data. This is used to update data 103. Then at 212, data is obtained from external systems 230, for example banking, credit and accounting data that is made available by third party sources. It will be appreciated that step 212 may be repeated at various stages in method 210, rather than requiring all external data be collected from the outset.

[00133] Functional block 213 represents a process including automated processing based on quantitative data. If this produces a threshold score (see decision 204), then the application proceeds to a loan parameters algorithm. Otherwise, the method proceeds to second-phase processing, which includes the defining of manual tasks at 215. These are coordinated by a manual task coordination engine 240 (for example as part of module 109) until all tasks are completed at 216. Each task, when completed, provides a quantitative input (for example a numerical value), and these are scored at 217. It will be appreciated that the manual task may consider qualitative data. [00134] Functional block 218 represents the actuation of a loan parameters algorithm based on data derived from the applicant, external systems, and (where relevant) scores from manual tasks. Assuming threshold conditions for loan approval are satisfied, this results in generation of an output indicative of a loan offer (with defined parameters) at 219, which becomes available to the applicant at 203.

Determination of Credit Score Based on Default Risk and Loss Given Default Parameters

[00135] Traditionally, credit bureaus produce a credit score which represents the risk of a default occurring on the customer (business or consumers credit file). The traditional approach, applies an algorithm that utilises inputs including customers past behaviour and demographic information to predict a single dependent variable "default occurrence". In the traditional models, the dependent variable underpinning the score is binary (will a default occur or not) with the score providing a probability of this event. The traditional models do not distinguish between different types or sizes of default. Finally, the score produced does not inform the credit provider as to the probability of collectability or the loss to the lender in the event of default (Loss Given Default).

[00136] It is typical for traditional credit scores to be calculated on a scale that represent the probability of the customer incurring a default on their credit file within the next 12 months.

[00137] There are two primary issues with the traditional approach which results in a large number of credit applicants being rejected (and leads to financial exclusion for a relatively large percentage of the market):

[00138] (1) The traditional model does not distinguish between different types or different sizes of default. The score produced for example does not inform the credit provider as to the probability of a default on a utility service bill versus a default on a home loan nor between the probability of a $250 default and a $500,000 default.

[00139] (2) By focusing on the probability of default and not giving full consideration to the Loss Given Default, the traditional approach overstates the risk of loss of capital to the lender. Empirical evidence from public bond markets indicates that the average recoverability on defaulted unsecured bonds is between 40% and 50%, irrespective of bond rating. [00140] Traditional credit bureau scores consider the parameter Probability of Default (PD) in arriving at a credit score. Embodiments of the invention described herein instead calculate a score which reflects Expected Loss (EL), and uses this score as a basis of credit decision determination. EL derived as follows:

EL = EAD x PD x LGD

Where: EAD = Exposure at default

PD = Probability of Default

LGD = Loss Given Default

[00141] Conventionally, large investment banks and corporate banks have used EL as a concept for large loans that are secured. However, such techniques have not been developed in the context of a technological framework that renders them suitable for unsecured lending to the SME market. Technology disclosed herein for performing analysis based on characteristics of directors' attributes (number, relationships, property value/status/equity, etc.) and other factors enables calculation of an LGD for a given unsecured loan application.

[00142] As an example, for a given applicant for a $10,000 loan, the Probability of Default (PD) may be 10% (i.e. $1 ,000). Conventional processes would likely result in a rejection of the application, because the default risk is higher than the maximum revenue that can be earned on the loan (assuming 9% interest rate the interest revenue would be $900). However algorithms of embodiments considered herein are applied to reveal, for example:

• A LGD of $5,000 or 50% of loan amount (because it has 3 directors, for example); and

• An EAD of $7,000 based on empirical knowledge of the average point in time at which a loan typically defaults and the resulting calculation of what the outstanding balance on the loan will be at that point in time.

[00143] Accordingly, the Expected Loss on the loan is calculated as follows: EL = EAD($7,000) x PD(10%) x (50%).

[00144] In this instance, the EL = $350. This can be compared to the Expected Return (ER) on the loan of $860 ($900 interest x 90% probability of not defaulting). For the sake of this example costs associated with processing and servicing the loan are disregarded. As the ER is higher than EL, a lender should be willing to lend using the embodiments considered herein.

[00145] A preferred approach is to make credit decisions with consideration to both Probability of Default and Loss Given Default.

[00146] Embodiments of the present invention enable credit decisions that take into consideration both Probability of Default and Loss Given Default by determination of an "Expected Loss", which is an objective determination of the expected loss on the loan. For example, one embodiment includes a computer implemented method for enabling determination of a credit score for a business, the method including: (i) applying a first algorithm thereby to determine a default probability score representative of risk of default in respect of a loan application; (ii) applying a second algorithm thereby to determine a Loss Given Default score representative of estimated loss in the event of default in respect of the loan application; and applying a third algorithm which uses input including the determined default probability score and determined loss given default score thereby to define an Expected Loss score and estimated $ loss for the applicant.

[00147] The first algorithm may be selected from various examples known in the art. In preferred embodiments, the second algorithm uses inputs including one or more of the following:

• The number of directors;

• The recency of removal of directors of the business;

• Whether the Directors are related;

• Age and other demographic information of the Directors;

For each director, a number of properties owned; For each property, whether the property is owned or rented;

• For each property, an estimated value for the property;

• For each property, a holding time for the property;

• For each property, an estimated annual growth rate for the property;

• For each property, an approximated equity proportion and/or value;

• For each property, a loan-to-value ratio for the property;

• The sector within which the borrowing entity operates;

• The amount of estimated debt held by the business;

• The amount of estimated debt held by each of the directors.

[00148] In a preferred embodiment, determination of a number of directors is one of the primary basis for a Loss Given Default score. Higher weightings are placed where directors are unrelated (with the term "related" being used in the context of family relationships) and when they reside at different addresses. FIG. 4B illustrates exemplary director scores according to one embodiment.

[00149] Weightings are also preferably applied for properties that are owned and rented. For example, some embodiments make use of weightings shown in FIG. 4C and FIG. 4D, which make user of non-linear relationships.

[00150] In some embodiments, weightings from FIG. 4C and FIG. 4D are applied to a director score from FIG. 4A thereby to determine a Loss Given Default score. An example is provided in FIG. 4E, which includes figures for a hypothetical business having four directors.

[00151] Additional parameters may also feed into the algorithm responsible for determining Loss Given Default score, for example those shown in FIG. 4F. The second algorithm is preferably thereby configured such that the Loss Given Default score is inversely proportional to equity in property attributable to the business' owner(s) and/or director(s). For example, the Loss Given Default in respect of a "recently-bought loan- funded" property is higher than for a property entirely owned by an applicant (with no mortgage).

[00152] In some embodiments wherein applying the second algorithm includes accessing one or more external information sources thereby to obtain details of one or more properties identified in the loan application. For example, based on address information, external databases are accessed thereby to determine estimated property values, ownership periods, housing value growth rates, and the like.

[00153] By way of example, one embodiment utilises onthehouse.com.au, which provides estimated values for house based on address information, size of land, recent sales, and other parameters. Other databases (such as realestate.com.au) may be used in addition to obtain similar (and in some cases more detailed and accurate) information. House value is used as an input into the algorithm (noting that house value is positively correlated with good credit and improves Loss Given Default).

[00154] Embodiments also consider if the applicant owns the house. If so, the process includes accessing data from third party databases thereby to estimate the growth rate of the house from the time they purchased it, and use this as an estimate of "equity value created" in the house since purchase. This variable is preferably entered into Loss Given Default assessment, and the higher the number the lower the Loss Given Default.

[00155] Steps discussed in this section may be incorporated into a process based on FIG. 2A.

Risk-Based Credit Pricing

[00156] Various embodiments include a process of defining one or more risk parameters for the loan application data set, and based on those defined one or more risk parameters, defining a loan offer having a set of loan rules. The loan rules are defined responsive to the defined one or more risk parameters, and include one or more of: a repayment schedule; rules for graduated release of loan funds; and loan interest rates. [00157] As an example, one embodiment uses an algorithm that has five independent variables (where each variable is the result of arrived at by combining and weighing other variables. The exemplary algorithm is as follows:

7.2^*77 + 1.4^*12 + 3.3^*13 + 0.6^*14 + 1.0^*15.

[00158] The results of the algorithm can fall into three categories:

[00159] Category 1 (Prime/Super Prime): a score above 2.99. In this instance embodiments are configured to define loan parameters thereby to price the loan aggressively (cheaply), with consideration to defined parameters for cost of funds and operating costs. The process is additionally configured to enable lending of larger amounts to this category; the higher the score above 2.99, the higher the possible maximum loan amount.

[00160] Category 2 (Near Prime): a score between 2.99 and 1 .80. In this category the process is configured to adjust both the interest rate and the maximum loan amount, depending on the score. The higher the score the lower the rate and the higher the loan amount, the lower the score the higher the rate and the lower the loan amount.

[00161] Category 3 (Sub Prime): Scores below 180. The process is configured to only lend a small loan amount to businesses with these scores (for example AU$5,000 or less). Embodiments then use customer's behaviour on an approved loan (i.e. repayment history) as feedback to an algorithm, at a later point in time thereby to determine whether the score is increasable to Category 2 (where the maximum loan amount is upwardly variable).

Synthetic Profit and Loss Data Generation

[00162] Various embodiments make use of synthetic profit and loss data generation thereby to assist in various stages of a loan approval process. For example, such data may be used in assessing loan, determining loan parameters, and so on.

[00163] One of the difficulties in assessing small businesses for credit, is the poor quality of available financial information. Profit and loss statements that are often used to assess credit for larger corporates are much less useful in the context of a small business for the following reasons:

• The business accounts often include personal transaction of the owner(s);

• The profitability is often "managed down" for tax purposes;

• Low accounting and finance budgets and lack of dedicated personnel often means poor quality inputs and preparation of accounts.

[00164] Embodiments considered herein utilise a technological process, applying computer technologies in a non-generic manner, that synthetically produces a profit and loss statement based on a combination of standardised P&L for the assessed businesses' industry and size and then "swaps out" individual P&L line items with actuals from the business where they can be validated and verified (for example by accessing bank statement transactional data and/or cloud accounting software systems).

[00165] FIG. 2B and FIG. 2C illustrate an exemplary methods 250 and 260 for generating a synthetic P&L data file.

[00166] Method 250 includes, at 251 , determining a P&L template for the relevant target business. For example, templates are be defined specific to industry, business size, and so on. Then, at 252, the template is populated with data values for individual line items based on data uploaded by the target business.

[00167] It will be appreciated that efficacy of the described technology increases with additional granularity in a template database. That is, as more templates are made available, the accuracy of matching of a given business to a predefined template based on high-level objectively defined factors increases.

[00168] In the case of method 260, a database of predefined profit and loss records is maintained, this including baseline/median data for a wide range of business of varying sizes across a range of industries. Blocks 261 and 262 represent processes whereby the industry and size of a target business are determined, allowing identification of an appropriate standardised profit and loss data set at 263. This provides a set of baseline data showing how a business is expected to perform based on collected historical empirical data.

[00169] A next line item to be processed, from a list of line items that are to be processed based on predefined rules, is identified at 253. For that line item, an external data source is accessed at 254. This may include a source of online banking data (for example obtained via a third party data provision service, or directly from electronic banking records), and/or accounting record data for the target business from an accounting software platform used by the target business (for example by way of integration with web-hosted accounting software packages).

[00170] Functional block 255 represents a process including applying a data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data. If the data is replaced (see decision 256), then the P&L data file is updated.

[00171] As general guidance, the following line items are preferably replaced:

• Revenue.

• Financing and interest cost.

• Cost of Goods Sold (sometimes replaced).

• Other operating expenses (where threshold objective confidence is attainable).

[00172] The process loops (see decision 258) until all line items requiring processing are processed. Then, as represented by block 259, a P&L data file is finalised. The result is a synthetic P&L which is a combination of information from the industry standard and from the business itself.

[00173] The method may include defining a score representative of the proportion of the line items for which the populated values are replaced (% replaced). "% replaced" is calculated to illustrate how much of the P&L is based on company information - higher % replaced = higher confidence. In the case of method 260, the synthetic P&L is readily suited to provide a financial comparison and line item comparison made on replaced line items to determine if the business is "better, worse or same" compared with industry average for the business size and sector.

[00174] FIG. 4A illustrates an exemplary user interface rendering synthetic P&L data file according to one embodiment, based upon the method of FIG. 3C. This shows line item values for a standardised P&L, adjustments to those values based on a business size scaling factor, whether line items are replaceable (i.e. whether replacement data is available), and whether they have in fact been replaced. Additional comparative data is provided, showing relationships between finance costs and net margins against industry averages.

Exemplary Client-Server Framework

[00175] In some embodiments, methods and functionalities considered herein are implemented by way of a server, as illustrated in FIG. 3. In overview, a web server 302 provides a web interface 303. This web interface is accessed by the parties by way of client terminals 304. In overview, users access interface 303 over the Internet by way of client terminals 304, which in various embodiments include the likes of personal computers, PDAs, cellular telephones, gaming consoles, and other Internet enabled devices.

[00176] Server 303 includes a processor 305 coupled to a memory module 306 and a communications interface 307, such as an Internet connection, modem, Ethernet port, wireless network card, serial port, or the like. In other embodiments distributed resources are used. For example, in one embodiment server 302 includes a plurality of distributed servers having respective storage, processing and communications resources. Memory module 306 includes software instructions 308, which are executable on processor 305.

[00177] Server 302 is coupled to a database 310. In further embodiments the database leverages memory module 306.

[00178] In some embodiments web interface 303 includes a website. The term "website" should be read broadly to cover substantially any source of information accessible over the Internet or another communications network (such as WAN, LAN or WLAN) via a browser application running on a client terminal. In some embodiments, a website is a source of information made available by a server and accessible over the Internet by a web-browser application running on a client terminal. The web-browser application downloads code, such as HTML code, from the server. This code is executable through the web-browser on the client terminal for providing a graphical and often interactive representation of the website on the client terminal. By way of the web- browser application, a user of the client terminal is able to navigate between and throughout various web pages provided by the website, and access various functionalities that are provided.

[00179] Although some embodiments make use of a website/browser-based implementation, in other embodiments proprietary software methods are implemented as an alternative. For example, in such embodiments client terminals 304 maintain software instructions for a computer program product that essentially provides access to a portal via which framework 100 is accessed (for instance via an iPhone app or the like).

[00180] In general terms, each terminal 304 includes a processor 31 1 coupled to a memory module 313 and a communications interface 312, such as an internet connection, modem, Ethernet port, serial port, or the like. Memory module 313 includes software instructions 314, which are executable on processor 311. These software instructions allow terminal 304 to execute a software application, such as a proprietary application or web browser application and thereby render on-screen a user interface and allow communication with server 302. This user interface allows for the creation, viewing and administration of profiles, access to the internal communications interface, and various other functionalities.

Conclusions and Interpretation

[00181] Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as "processing," "computing," "calculating," "determining", analyzing" or the like, refer to the action and/or processes of a computer or computing system, or similar electronic computing device, that manipulate and/or transform data represented as physical, such as electronic, quantities into other data similarly represented as physical quantities.

[00182] In a similar manner, the term "processor" may refer to any device or portion of a device that processes electronic data, e.g., from registers and/or memory to transform that electronic data into other electronic data that, e.g., may be stored in registers and/or memory. A "computer" or a "computing machine" or a "computing platform" may include one or more processors.

[00183] The methodologies described herein are, in one embodiment, performable by one or more processors that accept computer-readable (also called machine-readable) code containing a set of instructions that when executed by one or more of the processors carry out at least one of the methods described herein. Any processor capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken are included. Thus, one example is a typical processing system that includes one or more processors. Each processor may include one or more of a CPU, a graphics processing unit, and a programmable DSP unit. The processing system further may include a memory subsystem including main RAM and/or a static RAM, and/or ROM. A bus subsystem may be included for communicating between the components. The processing system further may be a distributed processing system with processors coupled by a network. If the processing system requires a display, such a display may be included, e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT) display. If manual data entry is required, the processing system also includes an input device such as one or more of an alphanumeric input unit such as a keyboard, a pointing control device such as a mouse, and so forth. The term memory unit as used herein, if clear from the context and unless explicitly stated otherwise, also encompasses a storage system such as a disk drive unit. The processing system in some configurations may include a sound output device, and a network interface device. The memory subsystem thus includes a computer-readable carrier medium that carries computer-readable code (e.g., software) including a set of instructions to cause performing, when executed by one or more processors, one of more of the methods described herein. Note that when the method includes several elements, e.g., several steps, no ordering of such elements is implied, unless specifically stated. The software may reside in the hard disk, or may also reside, completely or at least partially, within the RAM and/or within the processor during execution thereof by the computer system. Thus, the memory and the processor also constitute computer-readable carrier medium carrying computer-readable code.

[00184] Furthermore, a computer-readable carrier medium may form, or be included in a computer program product.

[00185] In alternative embodiments, the one or more processors operate as a standalone device or may be connected, e.g., networked to other processor(s), in a networked deployment, the one or more processors may operate in the capacity of a server or a user machine in server-user network environment, or as a peer machine in a peer-to-peer or distributed network environment. The one or more processors may form a personal computer (PC), a tablet PC, a set-top box (STB), a Personal Digital Assistant (PDA), a cellular telephone, a web appliance, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine.

[00186] Note that while diagrams only show a single processor and a single memory that carries the computer-readable code, those in the art will understand that many of the components described above are included, but not explicitly shown or described in order not to obscure the inventive aspect. For example, while only a single machine is illustrated, the term "machine" shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[00187] Thus, one embodiment of each of the methods described herein is in the form of a computer-readable carrier medium carrying a set of instructions, e.g., a computer program that is for execution on one or more processors, e.g., one or more processors that are part of web server arrangement. Thus, as will be appreciated by those skilled in the art, embodiments of the present invention may be embodied as a method, an apparatus such as a special purpose apparatus, an apparatus such as a data processing system, or a computer-readable carrier medium, e.g., a computer program product. The computer-readable carrier medium carries computer readable code including a set of instructions that when executed on one or more processors cause the processor or processors to implement a method. Accordingly, aspects of the present invention may take the form of a method, an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of carrier medium (e.g., a computer program product on a computer-readable storage medium) carrying computer-readable program code embodied in the medium.

[00188] The software may further be transmitted or received over a network via a network interface device. While the carrier medium is shown in an exemplary embodiment to be a single medium, the term "carrier medium" should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more sets of instructions. The term "carrier medium" shall also be taken to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by one or more of the processors and that cause the one or more processors to perform any one or more of the methodologies of the present invention. A carrier medium may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Non-volatile media includes, for example, optical, magnetic disks, and magneto-optical disks. Volatile media includes dynamic memory, such as main memory. Transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise a bus subsystem. Transmission media also may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications. For example, the term "carrier medium" shall accordingly be taken to included, but not be limited to, solid-state memories, a computer product embodied in optical and magnetic media; a medium bearing a propagated signal detectable by at least one processor of one or more processors and representing a set of instructions that, when executed, implement a method; and a transmission medium in a network bearing a propagated signal detectable by at least one processor of the one or more processors and representing the set of instructions.

[00189] It will be understood that the steps of methods discussed are performed in one embodiment by an appropriate processor (or processors) of a processing (i.e., computer) system executing instructions (computer-readable code) stored in storage. It will also be understood that the invention is not limited to any particular implementation or programming technique and that the invention may be implemented using any appropriate techniques for implementing the functionality described herein. The invention is not limited to any particular programming language or operating system.

[00190] It should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, FIG., or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

[00191] Furthermore, while some embodiments described herein include some but not other features included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention, and form different embodiments, as would be understood by those skilled in the art. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[00192] Furthermore, some of the embodiments are described herein as a method or combination of elements of a method that can be implemented by a processor of a computer system or by other means of carrying out the function. Thus, a processor with the necessary instructions for carrying out such a method or element of a method forms a means for carrying out the method or element of a method. Furthermore, an element described herein of an apparatus embodiment is an example of a means for carrying out the function performed by the element for the purpose of carrying out the invention.

[00193] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

[00194] Similarly, it is to be noticed that the term coupled, when used in the claims, should not be interpreted as being limited to direct connections only. The terms "coupled" and "connected," along with their derivatives, may be used. It should be understood that these terms are not intended as synonyms for each other. Thus, the scope of the expression a device A coupled to a device B should not be limited to devices or systems wherein an output of device A is directly connected to an input of device B. It means that there exists a path between an output of A and an input of B which may be a path including other devices or means. "Coupled" may mean that two or more elements are either in direct physical or electrical contact, or that two or more elements are not in direct contact with each other but yet still co-operate or interact with each other.

[00195] Thus, while there has been described what are believed to be the preferred embodiments of the invention, those skilled in the art will recognize that other and further modifications may be made thereto without departing from the spirit of the invention, and it is intended to claim all such changes and modifications as falling within the scope of the invention. For example, any formulas given above are merely representative of procedures that may be used. Functionality may be added or deleted from the block diagrams and operations may be interchanged among functional blocks. Steps may be added or deleted to methods described within the scope of the present invention.

Claims

CLAIMS:

1. A computer implemented method for enabling automated generation of a synthetic profit and loss data file for a target business, the method including:

identifying data representative of a target business, in respect of which a synthetic profit and loss data file is to be generated;

determining an industry parameter for the target business;

determining a business size parameter for the target business;

accessing a database that maintains baseline P&L data for a plurality of businesses, categorised by business size and industry;

extracting from the database a set of P&L data from the database based upon the determined industry parameter and determined business size parameter; populating a P&L data file with data values for individual line items based the extracted set of P&L data;

extracting, from data sources accessible via the Internet, either or both of:

transactional data for the target business from a source of online banking data;

accounting record data for the target business from an accounting software platform used by the target business; and

for each of at least a subset of the line items, applying a respective data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data.

2. A method according to claim 1 including defining a score representative of the proportion of the line items for which the populated value is replaced.

3. A method according to claim 1 wherein the baseline P&L data represents a predefined observed average for businesses of a given industry and business size, and wherein the method includes providing an output representative of performance of the target business relative to the predefined observed average.

4. A computer implemented method for enabling generation of a synthetic profit and loss data file, the method including:

identifying a target business;

selecting, from a set of available P&L templates, a specific P&L template for the target business;

populating the P&L template with data values for individual line items based on data uploaded by the target business;

extracting transactional data for the target business from a source of online banking data;

extracting accounting record data for the target business from an accounting software platform used by the target business; and

for each of at least a subset of the line items, applying a respective data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data.

5. A method according to claim 4 including defining a score representative of the proportion of the line items for which the populated value is replaced.

6. A computer implemented method for enabling processing of loan applications, constructing loan parameters and setting of loan pricing (risk based loan construction and pricing) the method including:

providing an interface that enables users of respective client terminals to upload respective loan application data sets;

for a given uploaded loan application data set:

a method for collecting information on a loan application, applying a protocol to determine the risk of the loan and then determining a loan structure, terms and price

(i) applying a first assessment protocol in respect of the application data set, wherein the first assessment protocol is an automated process performed based upon data contained in the application data set, and data obtained from one or more third party sources based upon data contained in the application data set; (ii) determining whether an output of the first assessment protocol meets first predefined requirements;

(iii) in the case that the predefined requirements are met, applying a first loan parameters algorithm thereby to define a loan offer, including loan terms and pricing, in respect of the loan application data set;

(iv) in the case that the predefined requirements are not met, progressing the loan application date set to a second assessment protocol;

(v) implementing the second assessment protocol in respect of the loan application data set, wherein implementing the second assessment protocol includes:

(a) defining a set of manual tasks;

(b) providing the defined set of manual tasks to a task management module, which is configured to coordinate assignment of the tasks across a plurality of distributed users;

(c) receiving quantitative data responses in respect of each of the defined set of manual tasks following manual completion of those tasks;

(vi) determining a combined output of the first and second assessment protocols;

(vii) determining whether the combined output meets second predefined requirements;

(viii) in the case that the second predefined requirements are met, applying a second loan parameters algorithm thereby to define a loan offer in respect of the loan application data set.

providing an interface configured to communicate to the users data representing outcomes of the first and/or second assessment protocols.

7. A method according to claim 6 including, based on at least one of the first and second assessment protocols, defining one or more risk parameters for the loan application data set, and based on those defined one or more risk parameters, defining a loan offer having a set of loan rules.

8. A method according to claim 7 wherein the loan rules are defined responsive to the defined one or more risk parameters, and include one or more of: a repayment schedule; rules for graduated release of loan funds; and loan interest rates.

9. A method according to claim 6 wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: business accounting data generated by the user via an accounting software package.

10. A method according to claim 6 wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: transaction data extracted from electronic banking records.

11. A method according to claim 6 wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: credit record data from one or more providers of credit record data.

12. A method according to claim 6 wherein the data obtained from one or more third party sources based upon data contained in the application data set includes: business information verification data from an independent business data registry.

13. A method according to claim 6 including generating a synthetic profit and loss data file.

14. A method according to claim 13 wherein generating a synthetic profit and loss data file includes:

identifying a target business;

determining an industry parameter for the target business;

determining a business size parameter for the target business;

accessing a database that maintains baseline P&L data for a plurality of businesses, categorised by business size and industry;

extracting from the database a set of P&L data from the database based upon the determined industry parameter and determined business size parameter;

populating a P&L data file with data values for individual line items based the extracted set of P&L data;

extracting, from data sources accessible via the Internet, either or both of:

transactional data for the target business from a source of online banking data; accounting record data for the target business from an accounting software platform used by the target business; and

for each of at least a subset of the line items, applying a respective data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data.

15. A method according to claim 14 wherein generating a synthetic profit and loss data file includes:

selecting, from a set of available P&L templates, a specific P&L template for the user's business;

populating the P&L template with data values for individual line items based on data uploaded by the user's business;

extracting transactional data for the user's business from a source of online banking data;

extracting accounting record data for the user's business from an accounting software platform used by the target business; and

for each of at least a subset of the line items, applying a respective data processing rule, wherein the data processing rule determines whether to replace the populated value with a replacement value derived from either or both of (i) the extracted transactional data; and (ii) the extracted accounting record data.

16. A computer implemented method for enabling determination of a credit score for a business, the method including:

applying a first algorithm thereby to determine a default probability score representative of risk of default in respect of a loan application;

applying a second algorithm thereby to determine a loss given default score representative of estimated loss in event of default in respect of the loan application; and

applying a third algorithm which uses input including the determined default probability score and determined loss given default score thereby to define a hybrid expected loss score and expected loss value, the later which is compared to expected return in order to make a lending decision.

17. A method according to claim 16 wherein the loss given default score is inversely related to attributable to the business' owner(s) and/or director(s).

18. A method according to claim 16 wherein the second algorithm uses inputs including one or more of the following:

a number of directors;

for each director, a number of properties owned;

for each property, whether the property is owned or rented;

for each property, an estimated value for the property;

for each property, a holding time for the property;

for each property, an estimated annual growth rate for the property;

for each property, an approximated equity proportion and/or value;

for each property, a loan-to-value ratio for the property.

19. A method according to claim 16 wherein the second algorithm includes:

determining a director score;

determining weights for director owned properties; and

determining weights for director rented properties.

20. A method according to claim 4 wherein determination of a director score includes determining a number of directors, and identifying relationships between directors.

21. A method according to claim 16 wherein the applying the second algorithm includes accessing one or more external information sources thereby to obtain details of one or more properties identified in the loan application.

22. A computer implemented method for enabling determination of a credit score for a business, the method including:

applying an algorithm thereby to determine a Loss Given Default score representative of estimated loss in event of default of a loan sum in respect of the loan application; wherein the Loss Given Default score is inversely related to equity in property attributable to the business' owner(s) and/or director(s); and

wherein the algorithm uses inputs including one or more of the following:

a number of directors;

for each director, a number of properties owned;

for each property, whether the property is owned or rented; for each property, an estimated value for the property;

for each property, a holding time for the property;

for each property, an estimated annual growth rate for the property;

for each property, an approximated equity proportion and/or value;

for each property, a loan-to-value ratio for the property

a sector within which the borrowing entity operates;

a amount of estimated debt held by the business;

a amount of estimated debt held by each of the directors.

23. A method according to claim 22 wherein the algorithm includes:

determining a director score;

determining weights for director owned properties; and

determining weights for director rented properties.

24. A method according to claim 23 wherein determination of a director score includes determining a number of directors, and identifying relationships between directors.

25. A method according to claim 22 wherein the applying the algorithm includes accessing one or more external information sources thereby to obtain details of one or more properties identified in the loan application.

26. A computer system configured to perform a method according to any one of claims 1 to 25.

27. A computer program configured to perform a method according to any one of claims 1 to 25.

28. A non-transitive carrier medium carrying computer executable code that, when executed on a processor, causes the processor to perform a method according to any one of claims 1 to 25.

Subject matter as described herein.