Predictive Model for Women's Sexual and Reproductive Health Decision-Making in Nigeria: A Machine Learning Approach Using the 2023–2024 NDHS Data

The research examined Nigeria Demographic and Health Survey (NDHS) data from 2023-2024 using machine learning algorithms to create forecasts that determined factors which affect women's sexual and reproductive health (SRH) choice processes.The NDHS showed three major barriers including inadequate adoptive rates of contraception at 15.3 percent and unmet family planning requirements affecting 21% of the population and varying maternal care availability across regions.The model checked for essential socio-economic factors and demographic aspects alongside regional indicators that affect women's ability to decide about their sexual reproductive health.Three machine learning algorithms; neural network, random forest and logistic regression were used to evaluate the NDHS data for predicting decision.Education level, wealth quintile, and geographic location were chosen through features selection method.Cross-validation was employed to train and validate the models for effective generalization.Spatial analysis for visualizing prediction results showed the areas that need maximum policy intervention.The research included measures to protect responsible insights from ethical concerns such as data privacy and model bias.The preliminary findings indicated that education status and wealth distribution seemed to produce influential results that can expose vulnerable regions for strategically focused intervention efforts.The data analysis presented evidence-based policy recommendations to both health practitioners and policymakers for women across Nigeria.The research findings demonstrated how predictive analytics enabled by machine learning can create transformative benefits in healthcare decision-making although they comply with Sustainable Development Goals (SDGs) 3 (health) and 5 (gender equality).