Analisis Kinerja Model Support Vector Machine dalam Prediksi Kasus HIV di Indonesia Berdasarkan Data Time Series

Erza, Muhammad Al-Ghifari
Prasetyaningrum, Putri Taqwa

Building of Informatics, Technology and Science
Vol 7 No 1 (2025): June (2025)

Accurate predictions of HIV cases are crucial in efforts to control the epidemic effectively in Indonesia. As the number of cases and the complexity of transmission factors increase, machine learning-based prediction methods are becoming increasingly relevant. This study analyzes the performance of the Support Vector Machine (SVM) model in forecasting the number of HIV cases in Indonesia using time series data from 2012 to 2024. The CRISP-DM methodology is used as the framework for the analysis process, starting from business understanding to model deployment. The dataset used includes secondary data from the Ministry of Health, such as SIHA, national surveillance, and reports from the Directorate General of Disease Prevention and Control (Ditjen P2P). The SVM model is selected due to its ability to handle non-linear data and limited data sizes, as well as its resilience to overfitting. Model evaluation is performed using MAE, RMSE, and MAPE metrics. The results of the study show that the SVR model with an RBF kernel provides good prediction accuracy, with MAE values of 691.34, RMSE of 823.11, and MAPE of 13% on the test data. Therefore, SVM can be an effective tool to support data-driven decision-making in HIV control efforts in Indonesia.