Child Malnutritional Status In Bangladesh: Machine Learning Approaches
Childhood malnutrition remains a significant concern in developing countries. This study utilizes machine learning algorithms to predict the malnutrition status of households based on data collected through the Multiple Indicator Cluster Survey (MICS) conducted by UNICEF in 2019 in Bangladesh. The dataset consists of variables such as prenatal care, education levels, sanitation facilities, and economic status. Factor Analysis for Mixed Data (FAMD) combined with Logistic Regression, Lasso Logistic Regression, Random Forest, and Support Vector Machine algorithms have been used in the advanced analysis. Bivariate analysis, including t-tests and chi-square tests, examines the association between predictor variables and malnutrition outcomes. The Random Forest model gives out the best results with high sensitivity, specificity, and accuracy. This suggests that Random Forests can be use in predicting child malnutrition status for households in Bangladesh. Yet, because of other influencing factors and potential biases in survey data means we might need more ongoing research and validation to get to a cohesive decision. As such new variables and new qualitative studies can be introduced to make the predictions more accurate.
Authors
- Md Mehedi Hasan Bhuiyan (ORCID: https://orcid.org/0009-0006-8563-3449)
- Poorna Sandamini Senaratne (ORCID: https://orcid.org/0009-0009-2008-2836)
- Shahd Alnofaie
Institutions
- University of Central Florida (US)
Publication Details
- Journal
- STARS (University of Central Florida)
- Published
- 2026-11-20
- Primary Topic
- Child Nutrition and Water Access
- Type
- article
- Field-Weighted Citation Impact
- 0.00