Analysis of Nutritional Status of Children in Karnataka Based on Machine Learning Techniques Using Indian Demographic and Health Survey Data

Malnutrition is caused when an individual gets very little or too many nutrients, resulting in health problems. In particular, “a deficit, excess, or imbalance of energy, protein, and other nutrients” negatively impacts the body's tissues and form. Malnutrition significantly contributes to infant mortality rates in developing nations, and India, as a developing country, experiences challenges associated with malnutrition in children under the age of five. The primary objective of this study is to analyze the factors influencing the nutritional status of under-five children in Karnataka, India, using data from the 2015-2016 Indian Demographic and Health Survey (IDHS). Logistic regression (LR), k-nearest neighbors (k-NN), support vector machines (SVM), random forest (RF), and Naïve Bayes (NB) are five prominent techniques in machine learning that are being utilized to successfully predict the factors affecting children's nutritional status. Body Mass Index (BMI), Height for Age Z score (HAZ), Weight for Age Z score (WAZ), and Weight for Height Z score (WHZ) are the main factors considered. Additionally, accuracy is used to do a systematic evaluation of the algorithms. Finally, the key factor impacting nutritional status in children was discovered to be HAZ based on accuracy, and the Random Forest produced the greatest findings and it was moderately superior to any other ML algorithms applied in this analysis.