<![CDATA[Stunting in toddlers remains a major public health challenge in Indonesia as it has long-term impacts on children’s growth and quality of life. Manual detection through community health posts often requires considerable time, is prone to errors, and lacks practical tools that can be independently used by the community. This study aims to develop an application based on the Naïve Bayes algorithm to support early detection of stunting risk among toddlers in the Bojongsari Community Health Center, Depok. The research employed a quantitative descriptive approach using the CRISP-DM method, involving data collection of children aged 0–59 months through observation, interviews, and documentation, followed by data cleaning, modeling with Naïve Bayes, and evaluation based on accuracy. The results indicate that the application successfully classifies toddlers’ nutritional status into normal or stunting categories with good accuracy, while providing a simple and user-friendly interface for independent use. The findings conclude that the implementation of the Naïve Bayes algorithm is effective in accelerating stunting risk detection and enhancing community participation in prevention efforts, which ultimately contributes to more efficient health services and reduced stunting prevalence. ]]>
Copyrights © 2025
