MACHINE LEARNING TO MANAGING MANUFACTURING COSTS AND REDUCE COSTS- AN APPLIED STUDY IN THE GENERAL COMPANY FOR FOOD PRODUCTS

Abstract

The food industry sector is facing increasing challenges due to rising production costs and growing local and global competition, which necessitates the search for modern approaches to cost management and operational efficiency. This study aims to examine the role of machine learning (ML) techniques in estimating and managing manufacturing costs by developing predictive models based on actual company data that contribute to cost reduction and improved resource utilization. The research adopts both the descriptive analytical and experimental methodologies, applied to the General Company for Food Products in Iraq. Historical data were collected regarding raw material costs, energy consumption, labor expenses, maintenance costs, and actual production over a defined time period. Subsequently, ML algorithms such as multiple linear regression, decision trees, and artificial neural networks were employed to construct models capable of forecasting future costs and identifying the most influential cost drivers. The findings revealed that the application of ML techniques provides a high predictive ability that significantly surpasses traditional cost estimation methods. Moreover, these techniques facilitate the identification and reduction of waste sources, resulting in noticeable cost savings. This, in turn, enhances the company’s competitiveness by reducing overall production costs and improving operational efficiency. The study recommends adopting intelligent cost management systems in the Iraqi food industry, while simultaneously developing digital infrastructure and training human resources to utilize artificial intelligence tools effectively. Such measures are expected to support sustainable industrial development and strengthen competitiveness in an increasingly demanding market environment.