Optimization of Imbalanced Class Using CTGAN and RSCV-Ensemble Learning for Clean Water Quality Classification

Abstract

Class imbalance is a common challenge in classification learning. This condition often leads to poor model performance in identifying minority class observations. This study aims to evaluate the performance of an Ensemble Learning model optimized using Randomized Search CV (RSCV) to classify clean water quality under imbalanced class distributions. To address the imbalance problem, the CTGAN technique is applied and compared with other oversampling methods like SMOTENC that also can handle mix data. The model performance is assessed using two sided independent t-test form different mean (accuracy, precision, recall, F1-score, and AUC-ROC) two models. The best model performance from Data Testing in this study is the Ensemble Learning model with RSCV combined with CTGAN oversampling followed by mean Accuracy of 92,8%, mean Precision of 90,23%, mean Recall of 90,98%, mean f1-score of 90,82%, and mean AUC-ROC 96,80% from 25 split data experiment. Almost all accuracy metrics showed statistically significant differences when tested using a two-sided independent t-test. Overall, the results indicate that CTGAN outperforms SMOTENC, and RSCV optimization improves performance compared to models without optimization. Not only accuracy, all different mean Recall metrics is significant, further supporting the superiority of CTGAN and RSCV-enhanced models.