Optimization of Resource Allocation in Production Management: A Machine Learning Approach

Abstract

This study explores the application of machine learning (ML) algorithms to optimize resource allocation in production management across various manufacturing sectors. Using a quantitative research approach, data were collected from 20 manufacturing firms employing ML solutions in production. The results indicate that ML-driven approaches, particularly reinforcement learning (RL) and supervised learning models, significantly enhance production efficiency by reducing downtime, improving cost efficiency, and optimizing resource utilization. On average, firms using ML achieved a 30% increase in cost efficiency and a 20% reduction in lead times. Reinforcement learning was found to be particularly effective in complex, variable production environments, while supervised learning provided reliable predictions in stable demand scenarios. However, companies encountered challenges with data quality, high initial costs, and the need for specialized skills. Practical implications suggest that phased implementation and continuous staff training can mitigate these challenges, ensuring smoother integration. The study concludes that ML offers substantial advantages in resource allocation, with further research recommended on the long-term impacts of ML across different industries and the role of advanced ML models, such as deep learning, in production optimization.