Utilizing Machine Learning Approach to Forecast Fuel Consumption of Backhoe Loader Equipment

This study addresses the challenge of forecasting fuel consumption for various categories of construction equipment, with a specific focus on Backhoe Loaders (BL). Accurate predictions of fuel usage are crucial for optimizing operational efficiency in the increasingly technology-driven construction industry. The proposed methodology involves the application of multiple machine learning (ML) models, including Multiple Linear Regression (MLR), Support Vector Regression (SVR), and Decision Tree Regression (DT), to analyze historical data and key equipment characteristics. The results demonstrate that Decision Tree models outperform other techniques in terms of precision, as evidenced by comparative analysis of the coefficient of determination. These findings enable construction firms to make informed decisions about equipment utilization, resource allocation, and operational productivity, thereby enhancing cost efficiency and minimizing environmental impact. This study provides valuable insights for decision-makers in construction project cost estimation, emphasizing the significant influence of fuel consumption on overall project expenses.