Improving the Efficiency of Production Processes by Reducing Human Errors Using Intelligent Methods

This paper addresses the critical challenge of human resource management in production processes, aiming to predict and mitigate human errors that significantly impact production costs. The study introduces a novel hybrid approach combining machine learning algorithms-K-Nearest Neighbors (KNN), Decision Tree, and Neural Networks-to forecast the occurrence of human errors effectively. Comprehensive production data was collected and analyzed, with each model’s predictive accuracy and effectiveness evaluated. The KNN algorithm demonstrated simplicity and effectiveness in pattern recognition, while Decision Trees provided clear decision rules and Neural Networks excelled in handling complex, non-linear relationships. The results reveal that integrating these models into production management systems can enhance operational efficiency and reduce costs by better anticipating and mitigating human errors. This research offers valuable insights into optimizing human resource allocation and improving overall production effectiveness.