MWMOTE optimization for imbalanced data using complete linkage

Abstract

Imbalanced data can result in classification errors, such as in WMMOTE, and can decrease its performance and accuracy. Clustering in MWMOTE can be optimized to improve synthetic data generation and improve MWMOTE performance. This study aims to optimize the MWMOTE algorithm's performance in the clustering process in making synthetic data with complete linkage (CL). The dataset used a variety of data ratios to handle imbalanced data. The decision tree was used to determine the performance of MWMOTE and CL-MWMOTE oversampling. CL-MWMOTE evaluation results provide better and optimal performance than MWMOTE and increase the precision, recall, f-measure, and accuracy of 0.53 %, 0.67 %, 0.66 %, and 0.67 %, respectively.