This study evaluates the Local Outlier Factor (LOF) algorithm for credit card fraud detection, emphasizing its effectiveness with highly imbalanced datasets. Unlike traditional methods that struggle with the rarity and variability of fraudulent transactions, LOF utilizes local density deviations to identify anomalies. Through a rigorous methodology involving data preprocessing, parameter tuning, and comparative machine learning analysis, LOF demonstrated a high recall rate and a balanced precision-recall trade-off, excelling at detecting subtle, localized fraud. Challenges like threshold setting and false positives were noted, with future research suggested on real-time integration and advanced feature engineering. The study underscores LOF's strengths, contributing to enhanced financial security strategies.
Copyrights © 2026