Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195124,
        author = {M Ganesh and J.V.V.S.Nithin Kumar and B.Nandini and A.Ganesh and G.S.K.Durga},
        title = {Credit Card Transaction Analysis for Fraud Pattern Identification Using Data Science},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8176-8181},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195124},
        abstract = {This project focuses on developing an intelligent and data-driven framework for analyzing credit card transactions and identifying fraudulent patterns using advanced Data Science and Machine Learning techniques. With the increasing adoption of digital payments, e-commerce, and online banking services, credit card fraud has become a major financial and security concern across the globe. Financial institutions face continuous challenges in detecting fraudulent transactions due to the high volume of daily transactions and the constantly evolving fraud strategies employed by cybercriminals. Traditional rule-based detection systems often struggle to adapt to these dynamic fraud patterns, resulting in delayed detection and increased financial losses. To overcome these limitations, the proposed study implements a machine learning-based fraud detection system capable of learning complex transaction behaviors and distinguishing between legitimate and fraudulent activities. The research utilizes the widely recognized Credit Card Fraud Detection dataset obtained from Kaggle, which contains anonymized transaction attributes along with fraud labels. The dataset is highly imbalanced, reflecting real-world scenarios where fraudulent transactions represent only a small fraction of total transactions. Therefore, comprehensive preprocessing steps are performed, including data cleaning, feature scaling, handling missing values, and applying techniques to manage class imbalance. Exploratory Data Analysis (EDA) is conducted to understand transaction distributions, feature relationships, and fraud occurrence patterns. Overall, this study presents a scalable, efficient, and reliable approach for credit card fraud detection that can assist financial institutions in strengthening transaction monitoring systems, reducing financial risk, and enhancing customer trust. The proposed framework also provides a foundation for future research in real-time fraud detection, integration with streaming data platforms, and adoption of deep learning techniques for further performance enhancement.},
        keywords = {Data Science, Fraud Detection, Credit Card Transactions, Machine Learning, XGBoost, Classification.},
        month = {March},
        }