<![CDATA[Outlier detection is a crucial stage in customer data analysis, as the presence of anomalies can significantly affect analytical outcomes and decision-making processes. This study aims to compare the performance of the Local Outlier Factor (LOF) and Elliptic Envelope (EE) algorithms in detecting outliers in customer behavior data. The dataset consists of 2,240 customer records with eight key features representing demographic characteristics, purchasing behavior, and responses to marketing campaigns. The research stages include data preprocessing, feature selection, normalization, and the application of the LOF and EE algorithms. The results indicate that LOF detects a larger number of outliers compared to EE, while EE tends to be more selective and focuses on extreme global deviations. A number of overlapping data points were also detected by both algorithms, indicating the presence of anomalies with consistent characteristics. Feature characteristic analysis reveals that each algorithm has a distinct and complementary detection focus. These findings suggest that a comparative approach between LOF and EE provides a more comprehensive understanding of customer anomaly patterns and supports the selection of appropriate outlier detection methods aligned with specific analytical objectives.]]>
Copyrights © 2026
