Exponential smoothing method against the gradient boosting machine learning algorithm-based model for materials forecasting to minimize inventory

Abstract

The optimization of resources and reduction of costs through efficient inventory management are paramount to organizational success. This study undertakes a comparative analysis of two distinct forecasting methodologies, Exponential Smoothing (ES) and Gradient Boosting (GB), within the framework of materials forecasting aimed at inventory minimization. Our study introduces innovation by methodically scrutinizing these approaches within a unified framework, shedding light on their merits and shortcomings. This comparative analysis gives practitioners a practical roadmap for the optimal forecasting strategy to streamline inventory management operations. Methodologies are evaluated based on their efficiency in predicting material demand, encompassing metrics such as accuracy, computational efficiency, and suitability across various inventory management scenarios. Response surface methodology entails refining processes to modify factorial variables’ configurations to attain a desired peak or trough in response. The SPSS results show that the ES method has 43.20%, surpassing the accuracy of the inventory optimization model, which stood at 65.08%. The response surface methodology results show that 45.20% profit was achieved for the variable and operational cost process parameters. This research seeks to unveil the traces of each method, facilitating decision-makers in selecting an optimal forecasting strategy tailored to their specific inventory management requirements. The analysis shows that the ES method surpasses the accuracy of the GB machine learning for material forecasting to minimize inventory.