Fraud detection on bank payments machine learning project

Buy Now ₹1001

This is a Data Science Project featuring Data Analysis to find out what factors indicate that a transaction might be fraud.

Then Deploying Machine Learning Algorithms such as Logistic regression, Random Forest and k-nearest neighbors to predict whether a transaction is fraud or not

The practice of obtaining financial gains by dishonest and unlawful means is known as financial fraud. Financial fraud, which is defined as the use of dishonest methods to obtain financial gains, has recently grown to be a serious threat to businesses and organizations. Despite several initiatives to curtail financial fraud, it continues to negatively impact society and the economy since daily losses from fraud amount to significant sums of money.

Several methods for detecting fraud were first introduced many years ago. The majority of old procedures are manual, which is not only time-consuming, expensive, and inaccurate, but also unworkable. There are more studies being done, however they are ineffective at reducing losses brought on by fraud. Conventional methods for detecting these fraudulent activities, like human verifications and inspections, are inaccurate, expensive, and time-consuming.

Machine-learning-based technologies can now be used intelligently to identify fraudulent transactions by examining a significant amount of financial data, thanks to the development of artificial intelligence. As a result, this study seeks to offer a novel model of fraud detection on bank payments utilizing the Random Forest Classifier Machine Learning Algorithm.

Our suggested system makes use of the Banksim dataset, and we have demonstrated that it is more effective than the current system by achieving train and test accuracy of 99%.

About Datasets :

Understanding the columns:

1. step is the unit of time which according to this data source is 1 hour

2. type is the transaction type (CASH-IN, CASH-OUT, DEBIT, PAYMENT and TRANSFER)

3. amount is the transaction amount

4. nameOrig is the transaction originator, this may indicate the person sending the payment

5. oldbalanceOrg is the initial balance (before transaction)

6. newbalanceOrig is the new balance (after transaction)

7. nameDest is the transaction recipient, person receiving the payment

8. oldbalanceDest is the initial balance before transaction.

9. newbalanceDest is the new balance after transaction.

10. isFraud is when a Fraud agent takes control of customers accounts and attempts to empty it by transferring to another account and then cashing out.

11. isFlaggedFraud is an illegal attempt to transfer massive amount of money in a single transaction.

Technology Used in the project :-

We have developed this project using the below technology
HTML : Page layout has been designed in HTML
CSS : CSS has been used for all the desigining part
JavaScript : All the validation task and animations has been developed by JavaScript
Python : All the business logic has been implemented in Python
Flask: Project has been developed over the Flask Framework

Supported Operating System :-

We can configure this project on following operating system.
Windows : This project can easily be configured on windows operating system. For running this project on Windows system, you will have to install
Python 3.7, PIP, Django.
Linux : We can run this project also on all versions of Linux operating systemMac : We can also easily configured this project on Mac operating system.

Installation Step : -

python 3.6.8
command 1 - python -m pip install --user -r requirements.txt
command 2 - python app.py