Predicting Employees’ Turnover in IT Industry using Classification Method with Feature Selection

Nowadays many IT companies are concerned about retaining their employees due to the competitiveness of employment landscape where highly skilled and quality IT knowledge workers are in huge demand. However, the growing pace of technological change and the socio-economic factors have transmuted employees in various organizations on how best to make their skills and talents proffered to be more attractive toward employers. Challenges pertaining to the turnover rate can be attributed to several factors such as failure employees to meet the company’s objectives, less motivating work environment, employees losing out to their employers, their skills are not put to best use, low wages, and many other turnover factors. On the other hand, the growing interest of machine learning (ML) lead to the prediction of the turnover factors. This research aims to explore the factors contributing to high turnover rate based on employee productivity using ML. For this purpose, dataset of 1,470 employees with 26 variables undergo feature selection processing which is to identify the correlation between employees’ productivity and turnover features which are (i) Pearson’s Square for categorical value and (ii) Correlation for numerical value have been applied to the dataset. The analysis shows higher accuracy after going through feature selection (18 variables) instead of without feature selection (26 variables). Thus, the best algorithm that can be used for the prediction of employees’ turnover is Random Forest with a model accuracy value of 87.76%, precision 0.643, recall 0.75, and F1-Score of 0.692.