Prediction of Construction Waste Generation Using Machine Learning for Optimized Management Strategies

The construction industry is a significant contributor to global waste generation, necessitating innovative approaches to streamline waste management processes. This study explores the application of machine learning techniques to predict the volume of waste generated by construction projects, thereby facilitating more effective waste management strategies. Utilizing machine learning models such as random forest regression, this study develops a predictive framework that integrates both categorical variables such as labor productivity and technology adoption and continuous variables, including project size, duration, number of floors, quantity of materials used and the total quantity of waste generated. The performance of the predictive models is evaluated using key statistical metrics from regression analysis. The findings aim to deliver valuable insights that could lead to proactive and data-driven decision-making in managing construction waste. Ultimately, seeking to contribute to a more sustainable and environmentally conscious construction industry by enhancing the predictability and thus the management of construction waste.