THESIS

Hybrid Machine Learning Model Base on Smoteenn Voting Ensemble and Shap Analysis

for Stunting Risk Prediction

ABSTRACT

Stunting is a global public health problem with long-term mpacts on human capita quality and remains a major priority in Indonesia. In West Sumatra Province, the stunting prevalence in 2024 reached 23.6%, which is still above the national target of 14%. This study aims to develop a machine learning-based stunting risk prediction model that can address class imbalance, improve predictive accuracy and sensitivity and provide transparent model interpretability. The dataset used in this study was obtained from the 2023 Family Data Updating Program conducted by the Nationas Population and Family Planning Board (BKKBN) of West Sumatra Province comprising 115,579 households. The research stages included data preprocessing data splitting, class balancing on the training set using SMOTEENN, hyperparameter optimization, and classification modeling using Logistic Regression, Random Forest Support Vector Machine, and XGBoost. Furthermore, a Soft Voting Ensemble (SVE with accuracy-based weighting was developed to integrate the strengths of multiple classifiers. Model performance was evaluated using accuracy, precision, recall, anc F1-score metrics, while interpretability was analyzed using SHapley Additive exPlanations (SHAP). The results show that applying SMOTEENN consistently improved the accuracy and sensitivity of all evaluated models. The largest performance improvement was observed in Random Forest, while XGBoos demonstrated the most stable performance with an accuracy of 91,82% and a recal of 9 1.74%. The hybrid Soft Voting Ensemble combining Random Forest and XGBoosk achieved the best results, with an accuracy of 91.95% and a sensitivity of 93,21% in detecting households at risk of stunting. SHAP analysis identified household ize education level, dietary diversity, occupation type, and drinking water source as the most influential predictors of stunting risk. Overall, this study demonstrates tha integrating SMOTEENN, accuracy-weighted Soft Voting Ensemble, and SHAP produces an accurate, sensitive, stable, and interpretable stunting risk predictior model, which is highly relevant for supporting data-driven stunting interventior policies.

PUBLICATION

• Optimizing Air Quality Index Classification Using Multiple Machine Learning Models and Oversampling Techniques (link)
• Hybrid ensemble learning with SMOTEENN and soft voting for stunting risk prediction: A SHAP-based explainable approach (link)
• Hybrid Soft-Voting Ensemble Model with Smoteenn: An Efficient Learning Approach for Stunting Risk Prediction (link)