Predicting Urban Farming Participation Intention in the National Capital Region, Philippines using Machine Learning Approaches
2026 International Conference on Advances in Artificial Intelligence and Machine Learning (AAIML), (2026), pp. 916-921
Aviona Bianca S. Bernil
a
,
Jericho Nheil C. Colina
a
,
Godwin Aldrich M. Ablao
a
,
Alexander A. Hernandez
a
,
Roman M. De Angel
a
a College of Computer Studies and Multimedia Arts, FEU Institute of Technology Manila, Philippines
Abstract: This study employs predictive analytics through supervised machine learning to examine how environmental knowledge, green innovation, and AI-technological sustainability influence urban farming participation intention in the city of Manila. Quantitative research was conducted, through an online survey from the city of Manila residents, irrespective of prior farming experience. Six machine learning models, random forest, k-nearest neighbors, support vector machine, decision tree, logistic regression and gradient boosting, were trained and tested after the data preprocessing to determine the strongest predictors of urban farming participation intention. The Random Forest model, thus, found to be the most accurate in predicting, demonstrated best R2, with the lowest error rates for predicting urban farming intention. Both the feature importance and SHAP analyses identify environmental knowledge as the primary driver, followed by AI technological sustainability and green innovation. The results show that people with higher environmental literacy and who have better access to AI-driven technologies are more likely to participate in urban farming. The study concluded that the city of Manila urban farmers would benefit through environmental education technological accessibility, and green innovation. Research and practical implications are presented to extend the contribution of the study.