Imputing Data and Predicting Waste with Machine Learning in East Java

Indonesia's waste problem continues to be a pressing environmental issue, along with the increasing population and urbanization activities. The increase in population and changes in consumption patterns have led to a significant spike in waste generation in Indonesia. Machine learning-based approaches become highly relevant in supporting accurate predictive systems to estimate waste generation, so that it can be used as a basis for policy making and planning for more effective and sustainable waste management. However,the issue of missing data is a common challenge in environmental data processing, including in the recording of waste generation. Incomplete waste generation data can hinder accurate analysis and prediction, which are essential for effective environmental management planning. This study aims to analyze the effectiveness of various data imputation methods and to develop a predictive model for waste generation in East Java Province using a machine learning approach. The imputation techniques tested include Mean Imputation, K-Nearest Neighbor (KNN), and Interpolation, while the predictive models used include Random Forest, Gradient Boosting, and KNN Regression. The dataset was obtained from the official SIPSN (National Waste Management Information System) website. Model performance was evaluated using metrics such as Root Mean Square Error (RMSE). The results indicate that the combination of KNN Imputer with the Gradient Boosting prediction model is effective in addressing missing data and predicting waste generation in East Java Province, achieving an RMSE value of 0.147. These findings are expected to support more accurate decision-making in waste management planning for the province.