Stacked Ensemble Classifier for Adoption of Point-of-Collection Water Treatment Technology Among Households in Western Kenya

TheDispensersforSafeWaterprogramunderEvidenceActionpromotespoint of collection water treatment through the installation of chlorine dispenser gadgets in rural parts of Kenya. Although the initiative has improved access to safe drinking water, monitoring household adoption remained a challenge during the COVID-19 pandemic, which limited field-based data collection and led to increased dependence on phone surveys. In addition, technology adoption data are often imbalanced, which poses difficulties for traditional classification methods. This study aimed to develop and implement a stacking ensemble classifier to model the adoption of chlorine dispensers among households in western Kenya. Data were collected from 27,457 households. The analysis used structured household, promoter and spot check survey data. The key variables included chlorine availability, user knowledge, household demographics, and engagement with promoters. RF, ANN, and NB models were trained and evaluated individually, then combined using a stacked ensemble approach. The ensemble model outperformed all base learners, achieving the highest accuracy (69.1%) and AUC (0.6959). The variable importance analysis revealed that the presence of chlorine and the knowledge of the user were the strongest predictors of adoption. In conclusion, ensemble learning provides a reliable method for modeling behavioral adoption in public health interventions. The findings offer practical insights for programs and demonstrate the potential of machine learning in improving, targeting and monitoring of safe water initiatives in low-resource settings.