The world faces a notable challenge with a substantial increase in waste production, driven primarily by the rapid expansion of urban areas and industrial growth. The primary objective is to evaluate the effectiveness of machine learning models in forecasting Municipal Solid Waste (MSW) generation within a specific geographic region, considering its patterns in the amount of waste generated. In this paper, nine distinct machine learning and deep learning models are trained and experimented with, along with the two proposed models, to gauge their performance in forecasting the periodic volume of generated waste. To ensure a comprehensive assessment, two machine learning models, Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing, are implemented. The study utilizes daily waste data sets from multiple places, viz. Moratuwa, Dehiwala & Boralesgamuwa from Sri Lanka, Ballarat from Australia, Austin from Texas, and Austin Waste and Diversion dataset. In essence, this study serves as a comparative analysis evaluating the performance of the two models in both data sets. The results of this study show that both models have varying effectiveness in predicting waste generation at different locations. In addition, the results indicate that the proposed methods perform better than the ones evaluated.