<![CDATA[In today’s competitive digital era, data-driven decision-making is key to enhancing the efficiency of human resource management. One of the main challenges is objectively assessing the impact of salary increases on employee performance, which is often assumed to be a primary motivator but rarely proven quantitatively. This study conducts a comparative analysis of two data mining methods, Linear Regression and Decision Tree Regression, to assessing and predicting the impact of salary increases on employee performance. A case study was conducted at PT. Taipan Agro Mulia using the company’s internal historical data. The analysis shows that Linear Regression performed better with an R-Square value of 0.731 or 73.1%, indicating that 73.1% of the variation in employee performance can be explained by salary increases. In comparison, Decision Tree Regression achieved an R-Square value of 0.700 or 70.0%. Additionally, Linear Regression recorded lower prediction errors (MAE = 4.78; MSE = 38.60; RMSE = 6.21) than Decision Tree (MAE = 5.61; MSE = 66.41; RMSE = 8.15). These findings demonstrate that data analysis approaches can serve as a strong foundation for formulating strategic salary policies aimed at improving employee performance]]>
Copyrights © 2025
