Empowering Sustainable Waste Management: A Comparative Study of Machine Learning Models for Citizen Engagement

Everyone needs to take responsibility to achieve sustainable waste management since this practice addresses not only ecological issues but also serves as an essential sustainability requirement. This research explores machine learning solutions that increase public participation and environmental consciousness for sustainable waste protection. In the proposed work, the performance of logistic regression, random forest, KNN, and the decision tree algorithm has been evaluated through multiple classification metrics using waste composition and treatment data. The selection of these models occurred because they demonstrated strong capabilities when dealing with structured data classification tasks. Different statistical parameters measures, including accuracy with precision and recall and F1-score, evaluated the models. The Random Forest model shows the optimal performance by attaining 89% accuracy along with an F1 score of 86%, which qualified it as the best method to forecast citizen engagement behavior. The Decision Tree model implementation reveals effective potential for tree-based methodology as waste management solution frameworks. This study provides effective strategies to boost waste recycling rates and develops operational techniques to lower open dumping occurrences and participation enhancement initiatives. Through machine learning-based civic engagement approaches, the government jointly develops better waste management plans together with local communities. Technology cooperation between citizens leads to an enduring environment where people actively protect their environment.