Developing a Hybrid Regression-Metaheuristic Forecasting Model for University Solid Waste Generation

The purpose of this study is to investigate and compare forecasting trends university solid waste (USW) at a private in Bangkok using combination statistical metaheuristic algorithms. university’s municipality data was prepared, collected, converted so that it could be processed by decision support system. Historical available for 16 years beginning with fiscal year 2005. Factors influencing USW quantities include the number students, staffs, others. divided into two sets: learning sets test sets. first will examined multiple regression metaheuristics components. datasets differ density because factor collected on an annual basis. As data, recorded through system monthly second combined proposed method determine trend substituting prediction equation management. primary goal paper develop effective model deal problem combining techniques. Based empirical analysis indicators’ USW’s from 2005 2020, we find hybrid based linear performs well all performance measures mean absolute percentage error (MAPE), deviation (MAD), square (MSE). These findings may useful preparation, configuration, implementation management university.