T

Transaction Monitoring System

This application detects potential money laundering cases from dataset of millions of transactions in just 2 clicks.

T

Transaction Monitoring System

This application detects potential money laundering cases from dataset of millions of transactions in just 2 clicks.

The problem Transaction Monitoring System solves

Problem

Money laundering is the illegal process of concealing the origins of money obtained illegally by passing it through a complex sequence of banking transfers or commercial transactions. The estimated amount of money laundered globally in one year is 2 - 5% of global GDP, or $800 billion - $2 trillion in current US dollars. It calls for more equipped monitoring system to monitor transactions.

Our Solution

Anti-money laundering (AML) transaction monitoring software allows banks and other financial institutions to monitor customer transactions on a daily basis or in real-time for risk. Our solution will automate the whole process of detecting a suspected money laundering case in just two clicks.

Challenges we ran into

Data Imbalance

We had a dataset which is imbalanced. The number of fraud transactions were quite less as compared to clean transactions. We went through different research papers. And we tried different techniques to solve this problem and finally we used ensemble random forest classifier to deal with this problem and achieved a impressive accuracy with training as well as testing data.

Discussion