Purpose: This research aims to address the methodological challenges posed by imbalanced data in classification tasks, where minority classes are severely underrepresented, often leading to biased model performance. It evaluates the effectiveness of hybrid sampling techniques specifically, the Synthetic Minority Oversampling Technique combined with Neighborhood Cleaning Rule (SMOTE-NCL) and with Edited Nearest Neighbors (SMOTE-ENN) in improving the predictive performance of ensemble classifiers, namely Double Random Forest (DRF) and Extremely Randomized Trees (ET), with a focus on enhancing minority class detection.
Methods: A total of eighteen simulated scenarios were developed by varying class imbalance ratios, sample sizes, and feature correlation levels. In addition, empirical data from the 2023 National Socioeconomic Survey (SUSENAS) in Riau Province were employed. The data were partitioned using stratified random sampling (80% training, 20% testing). Models were trained with and without hybrid sampling and optimized through grid search. Their performance was evaluated over 100 iterations using balanced accuracy, sensitivity, and G-mean. Feature importance was interpreted using Shapley Additive Explanations (SHAP).
Results: DRF combined with SMOTE-NCL consistently outperformed all other models, achieving 87.56% balanced accuracy, 82.17% sensitivity, and 86.75% G-mean in the most extreme simulation scenario. On the empirical dataset, the model achieved 76.37% balanced accuracy and 75.49% G-mean.
Novelty: This study introduces a novel integration of hybrid sampling techniques and ensemble learning within an interpretable machine learning framework, providing a robust solution for poverty classification in imbalanced datasets.

Purpose: This study explores diabetic retinopathy (DR), a complication of diabetes leading to blindness, emphasizing early diagnostic interventions. Leveraging Macular OCT scan data, it aims to optimize prevention strategies through tree-based ensemble learning.
Methods: Data from RSKM Eye Center Padang (October-December 2022) were categorized into four scenarios based on physician certificates: Negative & non-diagnostic DR versus Positive DR, Negative versus Positive DR, Non-Diagnosis versus Positive DR, and Negative DR versus non-Diagnosis versus Positive DR. The suitability of each scenario for ensemble learning was assessed. Class imbalance was addressed with SMOTE, while potential underfitting in random forest models was investigated. Models (RF, ET, XGBoost, DRF) were compared based on accuracy, precision, recall, and speed.
Results: Tree-based ensemble learning effectively classifies DR, with RF performing exceptionally well (80% recall, 78.15% precision). ET demonstrates superior speed. Scenario III, encompassing positive and undiagnosed DR, emerges as optimal, with the highest recall and precision values. These findings underscore the practical utility of tree-based ensemble learning in DR classification, notably in Scenario III.
Novelty: This research distinguishes itself with its unique approach to validating tree-based ensemble learning for DR classification. This validation was accomplished using Macular OCT data and physician certificates, with ETDRS scores demonstrating promising classification capabilities.