Nothing Special   »   [go: up one dir, main page]
Scribd Logo
Upload

Welcome to Scribd!

  • 18 views

    Project Zero

    Uploaded by

    sandravinod033

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Project Zero

    Uploaded by

    sandravinod033
    18 views15 pages

    Original Title

    project_zero

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    18 views15 pages

    Project Zero

    Uploaded by

    sandravinod033

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 15

    FRAUD DETECTION

    ON BANK
    PAYMENTS

    GUIDED BY SUBMITTED BY
    Mrs . ARATY V SANDRA V V
    ASSISTANT PROFESSOR S3 MCA
    DEPARTMENT OF MCA KVE22MCA-2014
    LITERATURE SURVEY
    INTRODUCTION

    Fraud detection in banks using machine learning is the application of artificial


    intelligence and data analysis techniques to identify and prevent fraudulent
    activities in financial transactions.
    Banks collect a vast amount of transaction data, including account activity,
    card transactions, online banking sessions, and more. This data serves as the
    foundation for fraud detection.
    One of the key aspects of fraud detection is identifying anomalies or unusual
    patterns in transaction data. Machine learning models can flag transactions
    that deviate significantly from expected behavior, which may indicate fraud.
    Machine learning (ML) has been shown to be an effective tool for fraud
    detection.
    ML models can be trained on historical data to learn the patterns associated
    with fraudulent transactions. Once trained, these models can be used to
    identify new fraudulent transactions as they occur.
    This literature survey provides a comprehensive overview of the current state
    of knowledge on ML for fraud detection on bank payments. It aims to identify
    the key findings, debates and to provide a context for the proposed research.

    3
    RELATED WORKS

    20XX 4
    SUMMARY RELATED WORKS

    SI.NO TITLE AUTHOR YEAR

    1 A model for rule based fraud S.Rajani, Prof.M. 2012


    detection in telecommunications Padmavathamma
    2 Review of machine learning Rejwan Bin Sulaiman, Vitaly 2022
    approach on credit card fraud Schetinin & Paul San
    detection
    3 Financial Fraud Detection Based on Abdulalem Ali, Shukor Abd 2022
    Machine Learning Razak
    4 Online payment fraud: from Sebastiano Rossi, Ermic Zvizdic, 2023
    anomaly detection to risk Thomas Domenig
    management
    5 Intelligent financial fraud detection: Jarrod West, Maumita 2016
    A comprehensive review Bhattacharya
    A MODEL FOR RULE BASED FRAUD DETECTION IN
    TELECOMMUNICATIONS

    The Telecommunications industry generates and stores a tremendous


    amount of data .The amount of data is so great that manual analysis of the
    data is difficult. The need to handle such large volumes of data led to the
    development of knowledge-based expert systems

    The problem with this approach is that it is time consuming to obtain the
    knowledge from human experts .As consumers are putting more of their
    personal information online and transacting much more business over
    computers , Telecommunication fraud occurs .
    This paper provides a detailed classification algorithm like the C4.5
    algorithm for rule-based fraud detection. The C4.5 algorithm is a popular
    choice for rule-based fraud detection because it is relatively simple to
    understand and implement. It is also able to learn complex rules from data,
    which is important for detecting fraud.
    This paper focuses on the problem of finding fraudulent customers using
    rule based systems, and gives the specific method to forecast the
    behaviour of malicious arrearage.
    6
    REVIEW OF MACHINE LEARNING APPROACH ON
    CREDIT CARD FRAUD DETECTION

    Most financial institutions have increasingly made business


    facilities available for the public through internet banking. Credit
    card fraud is considered a challenge which banks and financial
    institutions are facing. It occurs when unapproved individuals use
    credit cards for gaining money or property using fraudulent means.

    The paper examines various techniques used to detect fraudulent


    credit card transactions and finally proposes a better technique for
    credit card fraud. The machine learning algorithms which are used
    here are LR, Decision trees, Random Forests, Support Vector
    Machine , Neural networks .
    This paper involve the use of a federated learning concept that
    follows the framework for banks and financial institutions to
    collaborate for training the ML model.
    FINANCIAL FRAUD DETECTION BASED ON
    MACHINE LEARNING

    Financial fraud, considered as deceptive tactics for gaining financial


    benefits, has recently become a widespread menace in companies and
    organizations.

    Financial fraud is the act of gaining financial benefits by using illegal and
    fraudulent methods Financial fraud can be committed in different areas,
    such as insurance, banking, taxation, and corporate sectors. Credit card
    fraud is the most popular fraud type addressed using ML techniques.

    This paper aim to identify financial fraud transactions based on machine


    learning methods and to discover datasets applied in the ML-based
    financial fraud detection .

    SVMs, DTs and Random forests algorithm used in this paper. It also
    describes the research methodology, including the search criteria, study
    selection, data extraction, and quality evaluation.
    ONLINE PAYMENT FRAUD: FROM ANOMALY
    DETECTION TO RISK MANAGEMENT

    Online banking fraud occurs whenever a criminal can seize accounts and
    transfer funds from an individual’s online bank accounts. As fraudsters
    gain access to the payment systems as if they were the owners of the
    accounts, they cannot be identified based on the account access process.
    The assumption is that algorithms can detect anomalies in behavior
    during payment transactions.

    This paper defines three models that overcome these challenges:


    machine learning-based fraud detection, economic optimization of
    machine learning results, and a risk model to predict the risk of fraud
    while considering countermeasures. Our machine learning model
    alone reduces the expected and unexpected losses in the three
    aggregated payment channels by 15% compared to a benchmark
    consisting of static if-then rules.

    Algorithms here are bagged decision tree, isolated forest,Triaged


    model, Statistical risk model .
    INTELLIGENT FINANCIAL FRAUD DETECTION: A
    COMPREHENSIVE REVIEW

    Financial fraud is an issue with far reaching consequences in the


    finance industry, government, corporate sectors, and for ordinary
    consumers. Increasing dependence on new technologies such as cloud
    and mobile computing in recent years has compounded the problem.
    Traditional methods involving manual detection are not only time
    consuming, expensive and inaccurate, but in the age of big data they
    are also impractical. Not surprisingly, financial institutions have turned
    to automated processes using statistical and computational methods.
    CI-based detection algorithms are used in the this paper .This
    algorithms have several advantages over traditional machine learning
    algorithms for anomaly detection

    This paper presents a comprehensive review of financial fraud


    detection research using such data mining methods, with a particular
    focus on computational intelligence (CI)-based techniques.
    METHODS
    DATASET DESCRIPTION

     Dataset is taken from Kaggle and other Banking web sites

     Dataset Types : CSV/JSON/PARQUET

    SOFTWARE TECHNOLOGIES USED

     Python-Spark (Pyspark)

     Pandas & Keras

     Matplotlib (for drawing graphs)

     HTML/CSS/Javascript, for creating GUI interface


     IpyWidgets (Iron Python Widgets), for creating GUI
    interface
     Accuracy Evaluators
    MACHINE LEARNING ALGORITHMS USED

     Logistic Regression

     Random Forest

     Accuracy Metrics Used:-

    1. F1 – Score
    2. Accuracy
    3. Precision
    4. AUC (Area Under Curve)

    MODEL DEVELOPMENT & DEPLOYMENT PLATFORM

     Google Cloud (Colab)

     Can be executed in any Cloud, Linux, Windows, Android & iPhone O.S

     Login Module – with forgotten password recovery, Add new user


    GRAPHICAL USER INTERFACE

     Fully Menu Driven using HTML Button Click Events, the


    options are

    1. Load Data
    2. EDA-Exploratory Data Analysis
    3. Pre-Process Data
    4. Transform Data
    5. Build Model & Save
    6. Prediction (Single Input)
    7. Prediction (Bulk Input)
     When new data generates in Data Warehouse, the end user
    can create new model without any support from software
    engineers.
    THANK YOU

    20XX Literature survey 15

    You might also like