<![CDATA[Chronic nutritional deficiency issues such as stunting demand early monitoring accompanied by precise data documentation. Field practices indicate that Posyandu Belimbing still relies on conventional recording mechanisms to monitor toddlers' growth and development. This triggers risks of delayed intervention, data entry errors, and interpretation bias. As a solution, this research designs a web-based information system to classify the threat level of stunting through the application of the K-Nearest Neighbor (KNN) algorithm. The five metric indicators analyzed include the toddler's age, body weight, height, head circumference, and upper arm circumference. The classification mechanism relies on Euclidean Distance calculation by setting the nearest neighbor value k=3, which divides the output into low, medium, and high-risk zones. The software development cycle adopts the Agile framework, rolling from the initiation phase to deployment. System evaluation is proven through Black Box testing, White Box testing, and the distribution of questionnaire instruments to 15 field cadres. The functionality testing results confirm that all features operate without bugs, while the user satisfaction index reaches 82.44% (strongly agree category). In conclusion, this digital platform is highly capable of facilitating cadres to detect stunting vulnerability swiftly and in an organized manner.]]>
Copyrights © 2026
