Industrial Workers’ Efficiency in Indian Subcontinent: A Machine Learning Model Approach

The growing popularity of machine learning offers exciting possibilities for real-world applications. Since worker efficiency directly impacts a company's bottom line, especially for small and medium businesses (SMEs), implementing these tools can be a game-changer. By improving worker efficiency, machine learning can help SMEs minimize losses and drive growth. This research explores the potential of AI model not to replace workers but to uplift them. In this study, we try to find out the industrial workers' efficiency, especially in the Leather & Textiles industries, based on some parameters like expertise, education, salary, working hour, standard minute value (SMV), working position, key performance indicators (KPI) etc. The study investigates different regression models for predicting worker efficiency. Here we compare six models including Random Forest and XG Boost, using metrics like Mean Squared Error to find the best performing model. XG Boost and Histogram Gradient Boosting show the best results in predicting worker efficiency. XG Boost achieved high accuracy (R-squared around 0.78) with low errors (MSE around 0.01). Light GBM came in a close third, while Random Forest and Ada Boost did poorly. Machine learning techniques like XG Boost can significantly improve worker efficiency in the Indian subcontinent in leather-textile industries.