Uncovering Household Dietary Iron Inadequacy in Nigeria: A Data Science Exploration for Advancing Sustainable Development Goals

Abstract

Iron inadequacy remains a silent driver of hidden hunger, yet traditional survey analyses often miss its complexity. We applied a data science framework that integrates large-scale household data cleaning, feature engineering, and predictive analytics to uncover dietary iron inadequacy patterns across Nigerian households. Using nationally representative data from the 2018/2019 Nigeria Living Standard Survey (NLSS), we examined the socioeconomic and demographic factors influencing household iron intake. We categorized households into Adequate and Inadequate Intake groups based on daily iron consumption per adult equivalent and used logistic regression analysis to identify significant predictors. While 78.92% of households achieved adequate iron intake, 21.08% experienced inadequacy, with 10.11% facing severe deficiency. Higher household income, greater food expenditure, marital status, and increased dietary diversity significantly reduced the odds of iron inadequacy. In contrast, male-headed households, larger household sizes, and certain older age groups showed elevated risks. Higher education levels were associated with greater odds of iron inadequacy, a finding that may reflect emerging urban dietary transitions. Our findings highlight the multidimensional drivers of iron inadequacy in Nigeria and emphasize the need for targeted interventions that promote dietary diversity, address urban dietary shifts, and support vulnerable populations.