Implementation and Deployment of a Machine Learning-Based Credit Card Fraud Detection System
- Version
- Download 11
- File Size 489.81 KB
- File Count 1
- Create Date 11 June 2025
- Last Updated 11 June 2025
Implementation and Deployment of a Machine Learning-Based Credit Card Fraud Detection System
Authors:
Jaie Mude1, Gaurang Kumbhar2, Kkrish Pinjani3, Prof. Nikita Khawase4
1Department of Artificial Intelligence and Data Science, ISBM College Of Engineering, Pune
2Department of Artificial Intelligence and Data Science, ISBM College Of Engineering, Pune
3Department of Artificial Intelligence and Data Science, ISBM College Of Engineering, Pune
4Department of Artificial Intelligence and Data Science, ISBM College Of Engineering, Pune
Abstract: This project presents the development and implementation of a machine learning-based system for detecting fraudulent credit card transactions. Utilizing a highly imbalanced real-world dataset, the study explores various classification algorithms—K-Nearest Neighbors (KNN), Logistic Regression (LR), Support Vector Machines (SVM), and Decision Trees (DT)—to evaluate their effectiveness in fraud detection. Data preprocessing steps included class transformation for categorical visualization, normalization, and handling of imbalanced data. The system was developed using Python and Jupyter Notebook, employing libraries such as Scikit-learn, Pandas, NumPy, and Matplotlib for modeling, data analysis, and visualization. Among the models, KNN and Decision Trees demonstrated exceptional performance, each achieving 100% accuracy in detecting fraud cases. The final model was deployed as a user-interactive web application that enables real-time monitoring of transactions for potential fraud. This application aims to provide financial institutions with a robust, scalable, and efficient tool for enhancing transactional security and minimizing fraudulent activities.
Keywords – Implementation, machine learning, fraud detection, credit card transactions, KNN, Decision Tree, data preprocessing, imbalanced dataset, classification algorithms, deployment, Python, web application, real-time monitoring, financial security.
Download