What is Data Analytic?

Inthis new digital world, data is being generated in an enormous amount

which opens new paradigms. As we have high computing power and a large
amount of data we can use this data to help us make data-driven decision
making. The main benefits of data-driven decisions are that they are made up
by observing past trends which have resulted in beneficial results.
In short, we can say that data analytics is the process of manipulating data to
extract useful trends and hidden patterns that can help us derive valuable
insights to make business predictions.

Types of Data Analytics

There are four major types of data analytics:

1. Predictive (forecasting)
2. Descriptive(business intelligence and datamining)
3. Preseriptive (optimization and simulation)
4. Diagnostic analytics

Descriptive
Analytics
Diagnostic
Analytics Predictive
Analytics
Prescreptive
Analytics

Deals with Deals with Deals with How can we

Why did it What will make it
What
Happened happened happen in happen
in the Past in the Past the Future

Data Analuics and its Tipes

 I) Predictive Analyties
Predictive analytics turnthe data into valuable, actionable information. predictive
analyticsuses data to determine thc probable outcome of an event or a likelihood of
a situation occurring. Predictiveanalytics holds a variety of statistical techniques
from modelling, machine learning, data mining, and game theory that analyze
current and historical facts to make predictions about a future event.
Techniques that are used for predictive analvtics are:
Lincar Regression
Time Series Analysis and Forecasting
Data Mining
Basic Cornerstones of Predictive Analytics
Predictive modelling
Decision Analysis and optimization
Transaction profiling
2) Descriptive Analyties
Descriptive analytics looks at data and analyze past event for insight as to how to
approach future events. It looks at past performance and understands the
performance by mining historical data to understand the cause of success or failure
in the past. Almost allmanagement reporting such as sales. marketing. operations.
and finance uses this type of analysis.
The descriptive model quantifies relationships in data in a way that is often used to
classify customers or prospects into groups. Unlike a predictive model that focuses
on predicting the behaviour of a single customer, Descriptive analytics identifies
many different relationships between customer and product.
Common examples of Descriptive analyticsare company reportsthat provide
historic reviews like:
Data Queries
Reports
Descriptive Statistics
Data dashboard

3) Prescriptive Analy tics

Prescriptive Analytics automatically synthesize big data. mathematical seience.
business rule, and machine learning to make aprediction and then suggests a
decision option to take advantage of the prediction.
Prescriptive analytics goes beyond predicting future outcomes by also suggesting
action benefits from thepredictions andshowing thedecision maker the implication
of each decision option. Prescriptive Analyties not only anticipales what will happen
and when to happen but also why it will happen. F'urther. Prescriptive Analvtics can
suggest decision options on how to take advantage ola lulure opportunity or
mitigateafuture risk and illustrate he implicalion of ceach decision opion.
For example. Prescriptive Analytics can beneti hcalthcare strategie planning by
with data of
using analytics to leverage operalional and usage data combined ete.
external factors such as economic data, population demogrphy,
 4) Diagnostie Analyties
In this analysis, we generally use historical data over other data to answer any
question or for the solution of any problem. We try to find any dependency and
pattern in the historical data of the particular problem.
For example. companies go for this analysis because it gives a great insight into a
problem, and they also keep detailed inlormation about their disposal otherwise data
collection may turn out individual for every problem and it will be very time
consuming.
Common techniques used for Diagnostic Analytics are:
Data discovery
Data mining
Correlations
Life Cycle Phases of Data Analytics

Data Analytics Lifecycle:

The Data analytie lifecycle is designed for Big Data problen1s and data science
projects. The cycle is iterative to represent real project. To address the distinct
requirements for performing analysis on Big Data, step - by-step methodology is
needed to organize the activities and tasks involved with acquiring. processing.
analyzing. and repurposing data.
Phase l: Discovery -
The data science team learn and investigate the problem.
Develop context and understanding.
Cometo know about data sources needed and available for the project.
Theteam formulates initial hypothesis that can be later tested with data.
Phase 2: Data Preparation -
Steps to explore. preprocess, and condition data prior to modeling and
analysis.
load, and
It requires the presence of an analytic sandboX, the team execute,
transform, to get data into the sandbox.
Datapreparation tasks are likely to be performed multiple times and not in
predefined order.
Several tools commonly used for this phase are - Hadoop. AlpineMiner.
Open Refine, etc.
Phase 3: Model Planning -
Team explores data to learn about relationships between variables and
subsequently, selectskey variables and the most suitable models.
and
In this phase, data science team develop data sets for training. lesting,
production purposes. done in themodel
Team builds and executes models based on the vork
planning hase.
STASTICA.
Several tools commonly used for this phase are - Matlab.

Phase 4: Model Building -

Team develops datasets for testing, training, and production purposes.
Team also considers whether its existing tools willsulice lor running the
eNCCuting models.
models or if they need more robust environnent for
Octave. WEKA.
Free or open-sourCe lools - Rand PL/R.
Commercial tools - Matlab, STASTICA.
Phase5: Communication Results - modeling t0
After executing model team need to compare outcones of
criteria established lor success and failure.
. Teanm considers how besttoarticulate indings and outcomes to various
team members and stakeholders, taking into account warning.
assumptions.
Team shouldidentify key findings, quantifybusiness valuc. and develop
narrative to summarize and convey findings to stakcholders.
Phase6: Operationalize
The team communicates benefits of project more broadly and sets up pilot
project to deploy work in controlled way before broadening the work to
full enterprise of users.
This approach enables team to learn about performance and related
constraints of the model in production environmenton smallscale&nbsp.
and make adjustments before fulldeployment.
The team delivers final reports. briefings. codes.
Free or open-source tools- Octave, WEKA, SQL. MADIib.

Discoverv

Data
Pperationalis

Data Analytics Lifecycie

YCommunicat-j
Plarr9
Resui:

Id0del
Buding
Key Roles for Data Analytics project

There are certain key roles that are required for the complete and fulfiled
functioning of the data science team toexecute projects on analytics successfully.
The key roles are seven in number.
Each key plays a crucial role in developing asuccessful analytics project. There is
no hard and fast rule for considering the listed seven roles. they can be used fewer or
more depending on the scope of the project, skills of the participants. and
organizational structure.
Example -
For asmall, versatile team, these listed seven roles may be fulfilled by only three to
four people but a large project on the contrary may require 20 or more people lor
fulfilling the listed roles.
Key Roles for a Data analytics project:
1. Business User:
The business user is the one who understands the main area of
the project and is also basically benefited from the results.
This user gives advice and consult the team working on the
project about the value of the results obtained and how the
operations on the outputs are done.
The business manager. line manager. or deep subject matter
expert in theproject mains fulfils this role.

2. Project Sponsor:
The Project Sponsor is the one who is responsible to initiate the
project. Project Sponsor provides the actual requirements for the
project and presentsthe basic business issue.
He generally provides the funds and mcasures the degree of
value lrom thefinal output of the leam working on the projec1.
This person introduces the prime concern and brooms the
desired outpt.

3. Project Manager:
This person ensures that key milestone and purpose of the
project is mel on time and of the expecled qualiy.

4. Business Intelligence Analyst:

Business Intelligence Analyst provides business domain
perfection based ona detailed and deep understanding of the
data, key performance indicators (KPIs). kev matrix, and
business intelligence from areporting point of view.
 This person generally crcates lascia and reports and knows
about the data feeds and sOurces.

5. Database Adninistrator (DBA):

DBA facilitates and arrange the database cnvironment to
support the analytics need of the team working on aprojcct.
His responsibilities may include providing permission to key
databases or tables and making sure that the appropriate security
stages are in theircorrect places related to the data rcpositorics
Or not.

6. Data Engineer:
Data engineer grasps deep technical skills to assist wilh luning
SQL queries for data management and data extraction and
provides support for data intake into the analytic sandbox.
Thedata engineer works jointly with the data scientist to help
build data in correct ways for analysis.

7. Data Scientist:
Data scientist facilitates with the subject matter expertise for
analyticaltechniques, data modelling. and applying correct
analytical techniques or a given business issues.
He ensures overall analytical objectives are met.
Data scientists outline and apply analytical methods and procecd
towards the data available for the concerned projeet.
Importance of AnalyticalSandbox

What is an Analytical Sandbox?

An analytical sandbox is atesting environment that is used by data analysts and data
scientists to experiment with data and explore various analytical approaches without
affecting the production environment. It is a separate. isolated environment that
contains a copy of the production data, as wvell as the necessarv tools and resources
for data analysis andvisualization.
Analytical sandboxes are typically used for avariety of purposes. including testing
and validating new analytical approachcs and algorithms. trying out dilterent data
sets.collaborating andsharing work with colleagues, and testing new dala
visualization techniques and dashboards.

Some key features of an Analytical Sandbox may include:

1. A copy of the production data that is up-t0-date and accurate.
2. The same security controls as the production environment. protect
sensitive data.
3. The ability to handle large data sets andcomplex analytical queries
without affecting the performance of the production environment.
4. Tools and features for collaboration and sharing work with colleagues.
5. Flexibility to allow analysts to try out different analytical approaches and
techniques.
6. Clear documentation and support resources to heip analysis gel up to
speed quickly.

Analytical Sandbox's Essential Components Include:

1. Business Analytics (Enterprise Analytics) - The self-service Bl tools for

siluational analysis and discovery are part of business analvtics.
2. Analytical Sandbox Platform - The capabilities for processing. storing.
and networking are provided by the analytical sandbox plattorm.
3. Data Access and Delivery - Data collection and integration are made
possible by data access and delivery from a number of data sources and
data kinds.
4. Data Sources - Big data (unstructured) and lransactional dala (structured)
and oulside
are two types of data sources that can come from both inside
of thecompany. Examples of these sources include
exracts. fecds.
messages. spreadsheets. and docunments.
Graphical view ofAnalytical Sandbox Components

Business Analytic

Analytical sandbox

Data access and delivery

External Data Spreadsheet

Enterprise data Data Warehouse
Cloud
Unstructured
Documents

Importance of an Analytical Sandbox

1. unstructured and structured. can be combined and illered using analvtical

sandboxes.
2. Data scientists can carry oul complex analytices with the help of analvtical
sandboxes.
3. Analytical sandboxescnable working with data initially.
4. Analytical sandboxes make it possible to usehigh-performance computing
while processing Data from various sources. both internal and extemal.
both
5. databases because the analytics takes place inside the database itscll.
Advantages of an Analytical Sandbox

1. Acorporation can obtain knowledge and insight from its datamore

quickly thanks to the analyticalsandbox.
2. Without beginning a major BI project, analysts can immediately ig into
and handle vast amounts of data in an analytical sandbox environment that
is always available.
3. By giving your knowledgeable users more freedom, Analytical Sandbox
enables dynamic BI.
4. Giving the business space to prototype its data solutions enables the
business to determine what it wants independently withoul consulting IT.
which is another significant benefit for the business and IT team.

Applications of Analytical Sandbox

There are severalapplications of an analytical sandbox. including:

1. Data exploration and visualization: Analytical sandboxes can be used to
visualize and explore large datasets to identify patterns and trends, and to
create visualizations that help users understand and interpret the data.
2. Data modeling and analysis: Analytical sandboxes can be used to build
and test data models. such as predictive models or machine learning
algorithms, to understand how different variables or factors nay affect the
outcome of a particular problem or question.
3. Collaboration and sharing: Analytical sandboxes can be used to
collaborate withother users and share insights and findings with team
members or stakelholders.
4. Dala governance and security:Analytical sandboxes can be used to cnsure
that data is handled in asecure and complian! manner. as thev provide a
controlled environment where users can access and analyze data without
the risk of accidentally exposing scnsitive inlornmation.

Analytical Sandbox Key Criteria

1. There areseveral key criteria that an analy tical sandbox should meet in
order to be effective and useful lor data analysts and data seientists:
2. DataIntegrity: The sandbos should have acopy ol the produetion data that
is up-t0-date and accurate, so that analystscan work vith real data sets.
3. Dala Security: The sandbox should have the same seeurity controls as the
production environment, to ensure that sensiive data is protected.
 4. l'rormanee: The sandbox should be able to handle larpe data scts and
complex analytical queries withoul aflecting thc perlormalce of thc
produetion environment.
5. Collaboration: The sandbox should have tools and features that enable
data analysts and data seientists to collaboraleand sharc their work with
their collcagues.
6. Flexibility:The sandbox should be flexible enough to allow analysts to try
out dillerent analytical approaches and techniques without being
constrained by the production environment.
with clear
7. Ease of Use: The sandbox should be easy to use and navigate.
documentation and support resources available to help analysts get up to
speed quickly.
testing
An effective analytical sandbox should provide a safe and secure
explore and validate
environment that enables data analysts and data scientists to
the production
their work, while also protecting the integrity and stability of
environiment.

Whydo we use an Analytical Sandbox?

analytical sandboxcs:
There are several reasons whyorganizations use
algorithms: Analytical
1. To test andvalidate new analytical approaches and
analysts and data scientists
sandboxes provide a safe environment for data
algorithms before thev
to test and validate new analytical approaches and
are deployed in the production environment.
Totry out different data sets:Analytical sandboxes allow
analvsts to trv
2. the
out different data sets and see how they perform without affecting
production systenm.
analvsts to
3. To collaborate and share work: Analytical sandboxes enable
collaborate and share their work with their colleagues wvithout affecting
the production system. Analvtical
4. To test new data visualization techniques and dashboards:
sandboxes allow analysts to test new data visualization techniques and
dashboards without affecting the production system.
5. To ensure the integrity and stability of the produetion environment: Bv
providing aseparate testing environnent, analytical sandboses help to
ensure the integrily and slability of the production env ironment by
isolating it from any potential issues or changes that may arise during the
testing process.
Analytical sandboxes are an essential tool for data analysts and dala scientists. as
they provide asale and secure envirOnment for testing nd validating neW analhtical
approaches and lechniques.
i n n nl

Analvtical Sandbox vs Data Warehouse

1. An analytical sandbox and a data warchouse are tivo dillerent lypcs of

environments that arc used for different purposes in the ficld of data
management and analysis.
for
2. A data warehouse is a centralized repository of data that is designed
It typicall;
fast querying and analysis of large amounts of structured data.
stores historical data from a variety of sources and is used to support
business intelligence and decision-making activities.
is
3. Onthe other hand. an analytical sandbox is a testing environment that
used by data analysts and data scientists to experiment with data and
explore various analytical approaches without affccting the production
a copy of
environment. It is aseparate, isolated environment that contains
data
the production data, as well as the necessary tools and resources for
analysis and visualization.
querying and
A data warehouse is a centralized repository of data that is used for
that is used for
analysis, while an analytical sandbox is a testing environment
experimentation and validation of analyticalapproaches.