Finex is a leading financial service provider based out of Florida, US. It offers customers various products and business services through different channels, from in-person banking and ATMs to online banking. Over the last few years, Finex has observed that a significantly large number of unauthorised transactions are being made, due to which the bank has been facing a considerable revenue and profitability crisis. Many customers have been complaining about unauthorised transactions being made through their credit/debit cards. It has been reported that fraudsters use stolen/lost cards and hack private systems to access the personal and sensitive data of many cardholders. They also indulge in ATM skimming at various POS terminals such as gas stations, shopping malls, and ATMs that do not send alerts or do not have OTP systems through banks. Such fraudulent activities have been reported to happen during non-peak and odd hours of the day leaving no room for suspicion.
In most cases, customers get to know of unauthorised transactions happening through their cards quite late as they are unaware of ongoing credit card frauds or do not monitor their bank account activities closely. This has led to late complaint registration with Finex and by the time the case is flagged fraudulent, the bank incurs heavy losses and ends up paying the lost amount to the cardholders.
Finex is also not equipped with the latest financial technologies, and it is becoming difficult for the bank to track these data breaches on time to prevent further losses. The Branch Manager is worried about the ongoing situation. He wants to identify the possible root causes and action areas to develop a long-term solution that would help the bank generate high revenue with minimal losses.
Link to the dataset: https://www.kaggle.com/datasets/kartik2112/fraud-detection
Link to the video presentation: https://youtu.be/WBRCYe6gJa0
We performed an extensive EDA on the dataset. We built a machine learning model using Random Forest Classifier Algorithm which predicts whether an initiated credit card transaction is fraudulent with a 95% recall score. After performing a cost-benefit analysis, we found that our model has the potential to save costs to the bank up to 96% per month.
Here is what the fraud detection system looks like:
