Abstract / Summary
Traditional binary frameworks tend to combine the various aspects of unmet family planning needs into one general category. This study evaluates unmet family planning needs by first using conventional multinomial logistic regression to determine baseline demographic risk profiles. It then applies machine learning methods such as Random Forest and XGBoost to see if they can provide further insights into non-linear patterns and complex interactions between features that standard regression might miss. Using data from the Bangladesh Demographic and Health Survey (BDHS 2022), we built a multivariable multinomial logistic regression model. Additionally, we applied sophisticated ensemble classifiers such as Random Forest and XGBoost, paired with a synthetic hybrid resampling technique (SMOTE) to address severe class imbalance. Feature selection was conducted using the Boruta algorithm, and we used Shapley Additive Explanations (SHAP) to visualize complex global patterns and interaction effects. Bivariate analysis showed significant associations between unmet needs and maternal age, parity, wealth, residence, and decision-making power (p < 0.05). Multivariable logistic regression confirmed that having more children (4 or more) greatly increased the likelihood of unmet needs for spacing (aOR = 20.60) and limiting (aOR = 2.24). Wealth was notably protective against unmet needs for limiting, especially for the richest quintile (aOR = 0.48). Although SHAP analysis offered exploratory insights into complex, non-linear interactions between residence and factors such as parity and education, the predictive accuracy of tree-based models (Random Forest, XGBoost) was only moderate, with macro-averaged AUCs comparable to those of traditional regression. Therefore, population-level conclusions are most reliably drawn from the MLR model. The limitations of cross-sectional survey data as a diagnostic tool show that spacing needs are often fluid, transient, and shaped by relationships. Addressing the unmet need gap involves moving away from broad media campaigns toward localized counseling, ensuring stable rural spacing supplies, and involving husbands and mothers-in-law to turn reproductive healthcare into a shared household conversation.