This repository contains a machine learning project aimed at detecting fraudulent transactions in fintech banking systems. The project encompasses various stages including data preprocessing, feature engineering, model selection, training, and evaluation to build a robust fraud detection system.
The project was developed for the Statistical Machine Learning course at IIIT Delhi in Winter 2024.
- Data Preprocessing: Handling missing values, normalization, and transformation of financial transaction data.
- Feature Engineering: Creating meaningful features that enhance the model's ability to detect fraud.
- Model Training: Implementing multiple machine learning algorithms such as Logistic Regression, Random Forest, Gradient Boosting, etc.
- Evaluation: Assessing model performance using metrics like accuracy, precision, recall, F1-score, and ROC-AUC.
- Clone the repository and install the necessary dependencies using pip.
fintech-banking-fraud-transaction-jpmorgan.ipynb: The synthetic-data used in the project is especially provided by JP Morgan for research purposes which replicate the intricacies of real transactional data.fintech-banking-fraud-transaction-paysim.ipynb: We have used the Kaggle dataset "Synthetic Financial Datasets For Fraud Detection" generated by the PaySim mobile money simulator.
My IIIT Delhi batchmate Vashu also contributed in this project.
📌 Important: Please make sure to follow the guidelines and policies outlined by the institution regarding the use of shared coursework materials. Use this repository responsibly and avoid any violations of academic integrity. Codes are provided for reference purposes only. It's recommended to understand the codes and implement them independently.