Implementation of Machine Learning for Credit Card Fraud Detection using Logistic Regression and Gradient Boosting

Credit card fraud is a critical issue in digital financial transactions. This study aims to develop and evaluate fraud detection models using Logistic Regression and Gradient Boosting on an imbalanced dataset, where fraudulent transactions constitute only a small portion of the data. To address this imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied during preprocessing. Logistic Regression, used as a baseline model, achieved 95% accuracy, 78.6% precision, 55.9% recall, and a 65.3% F1-score. After applying class weighting and SMOTE, recall improved to 88.7%, but precision dropped to 52%, indicating that the model became overly sensitive and prone to false positives. Gradient Boosting initially produced better results, with 98% accuracy, 95.5% precision, 84.3% recall, and an 89.5% F1-score. After hyperparameter tuning and resampling, its performance improved further to 96.7% precision, 86.1% recall, and a 91.1% F1-score. These results indicate that Gradient Boosting is more effective in handling imbalanced data and offers greater reliability in detecting fraudulent transactions. The findings support the growing evidence in favor of ensemble learning techniques in fraud detection applications. This research contributes practical insights into improving the accuracy and security of machine learning-based fraud detection systems in financial services.