Fraud Detection System for Banking Transactions

TL;DR

This paper presents a machine learning framework for detecting financial transaction fraud using synthetic data, addressing class imbalance and model optimization for improved accuracy.

Contribution

It introduces a scalable fraud detection approach employing SMOTE and hyperparameter tuning within a CRISP-DM guided process, comparing multiple classifiers.

Findings

Random Forest achieved high accuracy in fraud detection.

SMOTE improved model performance on imbalanced data.

Hyperparameter tuning enhanced classifier effectiveness.

Abstract

The expansion of digital payment systems has heightened both the scale and intricacy of online financial transactions, thereby increasing vulnerability to fraudulent activities. Detecting fraud effectively is complicated by the changing nature of attack strategies and the significant disparity between genuine and fraudulent transactions. This research introduces a machine learning-based fraud detection framework utilizing the PaySim synthetic financial transaction dataset. Following the CRISP-DM methodology, the study includes hypothesis-driven exploratory analysis, feature refinement, and a comparative assessment of baseline models such as Logistic Regression and tree-based classifiers like Random Forest, XGBoost, and Decision Tree. To tackle class imbalance, SMOTE is employed, and model performance is enhanced through hyperparameter tuning with GridSearchCV. The proposed framework provides a robust and scalable solution to enhance fraud prevention capabilities in FinTech transaction systems. Keywords: fraud detection, imbalanced data, HPO, SMOTE