Competency Mapping A Study on the Competency Profile of Technical Employees of Mechanical Industries

Employee motivation and performance are two crucial aspects that determine the overall productivity and success of a Mechanical Industries. This study applies machine learning regression techniques Linear Regression (LR) and Random Forest Regression (RFR) to evaluate the relationship between employee motivation, work experience, and training with job performance. A dataset comprising 150 records was analyzed, containing quantitative measures for motivation score, years of experience, and total training hours as predictors, with job performance score as the target variable. Research Significance: The research holds significant value in understanding how motivational and experiential factors influence job performance in professional environments. In an era where organizations strive for higher efficiency and employee retention, identifying quantitative relationships between motivation, training, and performance becomes essential. Methodology: The methodology involved collecting and analyzing quantitative data representing 150 employee observations. Three key independent variables Motivation_Score, Work_Experience_years, and Training_Hours — were used as input parameters, while Job_Performance_Score served as the dependent variable. The data was preprocessed, normalized, and divided into training and testing subsets. Two machine learning models, Linear Regression and Random Forest Regression, were applied to predict job performance outcomes. Alternative (Input Parameters): The study utilized three measurable input parameters that directly influence job performance: Motivation_Score – Represents the employee’s level of enthusiasm, drive, and commitment toward their job. Work_Experience_years – Captures the cumulative professional experience of employees, reflecting their expertise and adaptability. Training_Hours – Indicates the amount of time invested in professional or skill development activities. These variables were carefully chosen as they collectively represent the psychological, experiential, and developmental dimensions that impact performance within an Mechanical Industries. Evaluation Parameter (Output Parameter): The primary evaluation parameter in this study was the Job_Performance_Score, which quantifies an employee’s efficiency, quality of work, and contribution to organizational goals. This score was modeled as a numerical output predicted from the three independent variables. By evaluating performance through a predictive model, the study aimed to establish measurable relationships between employee motivation, experience, and training — and their overall job effectiveness. Results: The results revealed that the Linear Regression model outperformed the Random Forest Regression model in terms of prediction accuracy and consistency. For the training data, LR achieved an R² value of 0.894, indicating a strong fit between predicted and actual job performance scores. The Random Forest model yielded a higher R² (0.97) during training but showed signs of overfitting with reduced performance on test data (R² = 0.82). The evaluation metrics confirmed that motivation had the highest correlation with job performance (r = 0.79), followed by work experience (r = 0.47) and training hours (r = 0.33). Conclusion: This study successfully demonstrated the application of predictive modeling in analyzing employee motivation and job performance. It was found that higher motivation, coupled with relevant work experience and adequate training, leads to improved job performance. Among the models tested, Linear Regression proved more effective and interpretable, making it a reliable tool for HR analytics.