Utilizing Single Exponential Smoothing for Early Detection and Forecasting of Stunting Cases in Madura
Fifin Ayu Mufarroha, Devie Rosa Anamisa, Achmad Jauhari, and Triyas Septiyanto

University of Trunojoyo Madura

Abstract

Stunting is still a serious public health concern in Indonesia. Stunting can have a negative impact on children^s health and development, as well as their productivity and learning abilities as adults. Efforts to eliminate stunting in Indonesia have been made in recent years, however there are still many cases that were not identified early and were not appropriately treated. Predicting the health of stunted individuals is thus one approach to this problem. Forecasting can benefit from the Single Exponential Smoothing technique. This method may be useful for diagnosing cases of stunting early and providing appropriate preventative actions. The purpose of this research is to create a prediction model for the number of stunted patients using the Single Exponential Smoothing method. This study relied on nutritional status data for children from 2018 to 2021. The Single Exponential Smoothing technique is used to anticipate future data by taking patterns in past data into consideration. The alpha value chosen was 0.5 by repeating the method and 0.1 as the second alpha value. This has caused the error value to drop by 10%. The outcomes of this study are expected to help connected parties design programs to address nutritional concerns more effectively and efficiently, enhance the quality of local community health, and aid in future planning and decision making in efforts to eliminate stunting.

Keywords: Forecasting, Stunting, Single Exponential Smooting, Madura

Topic: Artificial Intelligence and Data Science