Copyright © 2025 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{169550,
        author = {Gaurang kumbhar and Kkrish Pinjani and Jaie Mude and Nikita Khawase},
        title = {Credit Card Fraud Detection Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {1588-1592},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169550},
        abstract = {The dataset is first introduced by presenting its structure, which includes a detailed breakdown of all the attributes, along with their respective data types. This provides a comprehensive snapshot of the variables contained within each attribute, allowing for a clear understanding of the dataset's composition. A notable feature in the dataset is the "Class" attribute, which initially comes in the form of an integer. For ease of analysis and better visualization, this attribute is transformed into a categorical variable, or factor. In this transformation, the two values, '0' and '1,' are relabeled to provide more meaningful insights—'0' is assigned the label "Not Fraud," while '1' is relabeled as "Fraud." This step is crucial in simplifying the modeling process and making visualizations easier to interpret, especially in the context of fraud detection.
The class distribution within the dataset is then examined in detail, showcasing a significant imbalance between the number of non-fraudulent and fraudulent transactions. A bar chart is used to illustrate this, where the red bar, representing 284,315 entries, corresponds to non-fraudulent or legitimate transactions. In stark contrast, the blue bar, with only 492 entries, represents the fraudulent transactions. This overwhelming difference highlights the rarity of fraud cases within the dataset, which presents a challenge for machine learning models tasked with detecting these anomalies. Consequently, addressing this imbalance is a critical step in ensuring that the model accurately detects fraud cases despite their rarity within the dataset.},
        keywords = {Dataset structure, attributes and data types, class attribute transformation, categorical variable, fraud detection, class distribution, imbalanced dataset, non-fraudulent transactions, fraudulent transactions, data visualization, modeling process, anomaly detection, class imbalance, machine learning challenges, false negatives in fraud detection, transaction data analysis.},
        month = {November},
        }