Ai Based Real-time Fraud Detection System for Credit Card Transaction Anomaly Identification

Shreya Sunil Nehe; Prakash Devale

doi:10.71097/IJSAT.v16.i3.7443

Ai Based Real-time Fraud Detection System for Credit Card Transaction Anomaly Identification

Author(s)	Ms. Shreya Sunil Nehe, Dr. Prakash Devale
Country	India
Abstract	This study presents an AI-based real-time fraud detection system for credit card transaction anomaly identification using machine learning techniques. Leveraging the highly imbalanced Credit Card Fraud Detection dataset from Kaggle, which contains 284,808 transactions with only 0.2% fraudulent cases, the methodology includes data acquisition, preprocessing, exploratory data analysis, model development, and performance evaluation. Four supervised classifiers—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, and Logistic Regression—were implemented to detect fraudulent transactions. Data preprocessing involved scaling, careful handling of outliers, and an 80-20 train-test split to ensure model robustness. The models were evaluated using metrics sensitive to class imbalance, including precision, recall, F1-score, and ROC-AUC. Results demonstrate that while all models effectively identify legitimate transactions, the Decision Tree classifier achieved the best balance between interpretability and detection performance, with 75% precision and recall for fraudulent cases. However, false negatives remain a concern, indicating challenges inherent in imbalanced datasets. Visualizations such as confusion matrices, feature distributions, and model error rates provided insights into performance and potential overfitting. The study concludes that although the system performs well, further improvements could be achieved through ensemble methods, data balancing techniques like SMOTE, and cost-sensitive learning. Future work will explore advanced deep learning architectures, federated learning, and real-time streaming frameworks to enhance adaptability and scalability. This research underscores the potential of AI-driven systems to significantly reduce financial risk by enabling effective and efficient fraud detection in dynamic transactional environments.
Keywords	Credit Card Fraud Detection, Machine Learning, Imbalanced Dataset, Decision Tree, Real-Time Anomaly Detection, Data Preprocessing
Field	Engineering
Published In	Volume 16, Issue 3, July-September 2025
Published On	2025-07-31
DOI	https://doi.org/10.71097/IJSAT.v16.i3.7443
Short DOI	https://doi.org/g9vzdw

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2 Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Ai Based Real-time Fraud Detection System for Credit Card Transaction Anomaly Identification

Share this