Comparative Analysis of Random Forest, Logistic Regression and SVM for Stunting Prediction Using Anthropometric Data

Stunting remains a critical nutritional issue in Indonesia, significantly impacting the physical and cognitive development of children under five. Prompt and accurate detection of nutritional status is essential for early intervention. This study aims to predict toddlers' nutritional health using the Random Forest algorithm, based on age and height data. From an initial dataset of 120,998 anthropometric records, preprocessing steps—such as duplicate removal and nutritional status recategorization—resulted in a final dataset of 39,425 entries. The research methodology includes data collection, preprocessing, exploratory analysis, model training, handling class imbalance, and performance evaluation using accuracy, precision, recall, and F1-score. The study also compares the Random Forest model with Logistic Regression and Support Vector Machine (SVM). Results show that Random Forest outperforms the other models, achieving perfect classification metrics: Accuracy (1.00), Recall (1.00), F1-Score (1.00), and Cross-validation Accuracy (99.74%). These outcomes highlight Random Forest's robustness in classifying under-five nutrition data, making it an effective tool for rapid and reliable stunting risk detection. This research supports efforts to reduce Indonesia's stunting rate to below 20% by 2024, contributing to national health improvement strategies through technology-driven early diagnosis.