Scribd
Upload
16 views24 pages

Online Fraud Detection

This is one of my project

Uploaded by

Shivarani Beenamoni
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views24 pages

Online Fraud Detection

This is one of my project

Uploaded by

Shivarani Beenamoni
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

Online Payment Fraud Detection

with Machine Learning


-PRESENTED BY
-B182207
-B182038
UNDER THE SUPERVISION OF
-RAMYA MADAM
In this presentation, we will explore how
machine learning 
can detect and prevent online payment fraud,
one of the fastest-growing problems .
TABLE OF CONTENTS
1.Abstract
2.Introduction
3.Problem Statement
3.1.Fraud Detection
3.2.Fraud Detection process
4.Technologies Used
4.1.Machine learning
4.2.Python
5.Modules
6.Datset for Online Payment Fraud Detection
7.Progress Application
8.Advantages
9.System Requirements
10.Conclusion and Future Scope
Abstract-

Recent research has shown that machine learning techniques have been
applied very effectively to the problem of payments related fraud detection.
Such ML based techniques have the potential to evolve and detect
previously unseen patterns of fraud. In this project, we apply multiple ML
techniques based on Logistic regression and Support Vector Machine to the
problem of payments fraud detection using labeled dataset containing
payment transactions. We show that our proposed approaches are able to
detect fraud transactions with high accuracy and reasonably low number of
false positives.
Introduction

We are living in a world which is rapidly adopting digital payments


systems.
online payments companies are experiencing a very rapid growth in their
transaction volume.
An effective fraud detection system should be able to detect fraudulent
transactions with high accuracy and efficiency.
While it is necessary to prevent bad actors from executing fraudulent
transactions, it is also very critical to ensure genuine users are not
prevented from accessing the payments system.
Problem Statement

Online payment fraud stands as Major problem for worldwide financial


Institutions Annual lost due it scales to billions of dollars.
Today due to rapid growth in e-commerce online shopping or online
transaction is grown day by day. The mode of payment is done by
Online payment. The online payments are increasing day by day. It
was reported that there are almost 430 million credit and debit
across whole Europe. As the number of credit/debit card users
increasing, the fraudulent users are also increasing.
Fraud Detection

Fraud detection is a topic which is applicable to many industries including


Banking and financial sectors ,insurances , government agencies, and low
enforcement and more.
Through the use of sophisticated use of data mining tools ,millions of
transactions can be searched to spot patterns and detect fraudulent
transactions.
Fraud detection is a process of identifying fraudulent transactions.
Online payment fraud detection technic used to recognize fraudulent online
payment transactions so that customers are not charged for items that they
did not purchases.
Fraud Detection process
Technologies used

Machine learning
Machine learning is the scientific study of algorithms and static models that
computer system use in order to perform a specific task effectively without Using
the explicit instruction ,relaying on patterns and interface instead .

Machine learning algorithms build a mathematical model based on sample data ,


Known as training data in order to make prediction and decisions.

Machine learning algorithms are used in Email filtering , face recognition ,house
pricing prediction,etc.
Types of Machine learning algorithm
Supervised learning

Supervised learning, also known as supervised machine


learning, is a subcategory of machine learning and artificial
intelligence. It is defined by its use of label datasets to train
algorithms that to classify data or predict outcomes accurately.
Unsupervised learning

Unsupervised learning, also known as unsupervised machine learning, uses


machine learning algorithms to analyze and cluster unlabeled datasets.
These algorithms discover hidden patterns or data groupings without the
need for human intervention.
Reinforcement learning

Reinforcement learning is a machine learning training method based on


rewarding desired behaviours and/or punishing undesired ones. In general, a
reinforcement learning agent is able to perceive and interpret its
environment, take actions and learn through trial and error.
Modules
Module 1:Frame the problem
Module 2:Collect the raw data
Download data from Kaggle
Module 3: Import the Libraries
Pandas, numpy ,sklearn etc.
Module 4: Process the data for analysis.
Perform the logistic regression on data , explore the data.
Module 5:Perform in-depth analysis.
Module 6:Communicate results of the analysis
Data Flow diagram
Progress of Application
Advantages

The results obtained by the Logistic Regression Algorithm is best compare


to any other Algorithms.
Machine learning algorithms can identify unusual patterns or deviations from
normal behaviour in transactional data.
By “training” on historical data, the algorithms learn to recognize legitimate
transactions and flag suspicious activities that may indicate fraud.
Higher accuracy of fraud detection.
Less manual work needed for additional verification.
Fewer false declines.
Applications
Future Scope

The system prevents Fraudulent users from misusing the details of online
payment of the genuine users for their personal gain.

Creating an application to detect fraud online payments.

Creating Data base containing all relevant information of customers.

Provide Security to the customers at the transaction time.


Conclusion

In fraud detection, we often deal with highly imbalanced datasets. For the chosen
dataset , we show that our proposed approaches are able to detect fraud
transactions with very high accuracy and low false positives – especially for
TRANSFER transactions.

Fraud detection often involves a trade off between correctly detecting fraudulent
samples and not misclassifying many non-fraud samples. This is often a design
choice/business decision which every digital payments company needs to mak
e .We’ve dealt with this problem by proposing our class weight based approach.
References

A Survey of Credit Card Fraud Detection Techniques: Data and Technique


Oriented Perspective - Samaneh Sorournejad , Zojah , Ataniet.al -
November 2016
PayPal Inc. Quarterly results https:
//www.paypal.com/stories/us/paypalreports-third-quarter-2018-results
www.ijcrt.org © 2021 IJCRT | Volume 9, Issue 5 May 2021 | ISSN: 2320
-2882
► Websites
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
tp=&arnumber=5159014&que
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
tp=&arnumber=5762457&query
THANK YOU

You might also like