THESIS

Comparison of Machine Learning Algorithm Performance in Detecting Stunting with the Application

of Recursive Feature Elimination and Smote

ABSTRACT

Stunting remains a major global health issue that significantly impacts child growth and development. In Indonesia, the prevalence of stunting is still high, with Aceh Province reporting a rate of 31.2%, which is considerably above the national average of 21.6%. This condition necessitates a data-driven approach to support early detection and more effective nutritional interventions. This study aims to compare the performance of several machine learning algorithms in predicting children’s nutritional status, identify the most influential features affecting nutritional outcomes and develop an accurate and reliable predictive model. The dataset used is derived from the 2022 Indonesian Nutritional Status Survey (SSGI) for Aceh Province. Five machine learning algorithms were employed: Decision Tree, Random Forest, XGBoost, Support Vector Machine (SVM), and Logistic Regression. Data preprocessing involved simple imputation to handle missing values and nominal encoding for categorical variables. Furthermore, Recursive Feature Elimination (RFE) was applied for feature selection, and the Synthetic Minority Oversampling Technique (SMOTE) was utilized to address class imbalance. The experimental results indicate that models combining RFE and SMOTE significantly enhance recall and AUC-ROC performance. Among the evaluated models, the SVM model achieved the best performance with a recall of 96.75% and an AUC-ROC of 92.34%. Feature importance analysis using the SVM model with RFE and SMOTE identified Height/Length and Child Age as the two most influential features, with contribution scores of 0.436 and 0.370, respectively. The proposed predictive model demonstrates strong potential as a decision-support tool for early stunting detection in Aceh Province and can facilitate more targeted nutritional interventions.

PUBLICATION

Under Review