Prediction of employee attrition using Machine Learning algorithms

Paper ID: EIJTEM_2026_13_1_1-7

Author's Name: Dr.B.Shathya, R.Deepika, J.Keerthana, S.Steffy saron

Volume: 13

Issue: 1

Year: 2026

Page No: 1-7

Abstract:

Organizations face a serious problem with employee attrition, which has an impact on overall business performance, workforce stability and productivity. Machine learning based employee attrition prediction can assist companies in proactively identifying high-risk workers and putting retention plans into place. In order to create a precise forecast framework for employee attrition, this study investigates various machine learning algorithms. Numerous employee characteristics such as demographics, job roles, work environment and satisfaction levels are used in this study. Data preprocessing includes class imbalance treatment with the Synthetic Minority Over-sampling Technique (SMOTE) and categorical variable encoding. By doing this, model bias is avoided and minority class instances that is departing employees are fairly represented. The Grid Search Cross-Validation is used to train and refine hyperparameters for three machine learning algorithms Random Forest, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM). To assess these models’ efficacy in forecasting employee attrition important performance indicators like accuracy, precision, recall, F1-score, cohen's kappa, confusion matrix and ROC-AUC are used. The results indicate that Support Vector Machine (SVM) achieves the highest overall performance with an accuracy of 92.32% and the best ROC AUC score of 97.57%, making it the most effective at distinguishing between employees who will stay and who will leave. The study underscores the importance of selecting an appropriate predictive model to develop data-driven retention strategies, improve employee engagement and reduce turnover rates.

Keywords: K-Nearest Neighbor, Machine Learning, Random Forest, Support Vector Machine, Synthetic Minority Oversampling Technique.

References:

[1] J. Neha, R. Singh, and S. Khanna, “Machine learning applications in employee attrition prediction,” Journal of Artificial Intelligence in HR, vol. 45, no. 6, pp. 678–692, 2022.
[2] A. Vikram, P. Nair, and B. Reddy, “HR analytics for employee turnover: A data-driven approach,” International Journal of Data Science, vol. 38, no. 2, pp. 191–207, 2020.
[3] S. Priya, V. Kumar, and T. Joshi, “Real-time employee feedback and attrition prediction: A data-driven strategy,” Human Resource Analytics Journal, vol. 29, no. 3, pp. 341–357, 2018.
[4] M. Harish, L. Gupta, and R. Bose, “External job opportunities and compensation: Their impact on employee turnover,” Business and Economic Research, vol. 22, no. 4, pp. 412–427, 2016.
[5] P. Meera, G. Rao, and N. Shetty, “Work-life balance and employee retention: A study on organizational strategies,” International Journal of Workplace Psychology, vol. 17, no. 1, pp. 89–104, 2019.
[6] K. Arjun, R. Dixit, and P. Choudhary, “The impact of employee engagement on turnover intentions,” Journal of Organizational Leadership, vol. 34, no. 5, pp. 510–526, 2021.
[7] N. Rajesh, S. Iyer, and P. Menon, “Leadership style and its effects on employee retention,” International Journal of Management Studies, vol. 19, no. 3, pp. 276–291, 2015.
[8] R. Kiran, D. Sen, and P. Mishra, “The role of workplace culture in employee turnover: A case study approach,” Journal of Business Ethics, vol. 24, no. 2, pp. 132–148, 2017.
[9] T. Suman, R. Bhardwaj, and S. Chatterjee, “Artificial intelligence in HR: Predicting and preventing employee attrition,” AI & Business Review, vol. 50, no. 1, pp. 23–38, 2023.
[10] P. Ramesh, K. Agarwal, and A. Saxena, “Employee training and development as a retention strategy,” Journal of Human Resource Development, vol. 42, no. 4, pp. 299–315, 2020.
[11] V. Anita, S. Kapoor, and N. Malhotra, “Job satisfaction, psychological well-being, and employee attrition: A holistic perspective,” International Journal of Occupational Health, vol. 30, no. 3, pp. 178–193, 2021.
[12] N. El-Rayes, M. Fang, M. Smith, and S. M. Taylor, “Predicting employee attrition using tree-based models,” International Journal of Business Analytics, vol. 7, no. 2, pp. 1–15, 2020.
[13] B. Sirisha, R. V. Dhanalakshmi, and P. Padmaja, “Employee attrition prediction using feature selection with information gain and random forest classification,” Journal of Engineering Research and Application, vol. 12, no. 1, pp. 1–8, 2022.
[14] D. Alao and A. B. Adeyemo, “Employee attrition prediction using deep neural networks,” Computers, vol. 10, no. 11, p. 141, 2021.
[15] S. Alsheref, “Predicting employee attrition using machine learning approaches,” Applied Sciences, vol. 12, no. 13, p. 6424, 2022.
[16] P. Racherla, “Employee attrition prediction in a pharmaceutical company using machine learning techniques,” Benchmarking: An International Journal, vol. 27, no. 5, pp. 1579–1598, 2020.
[17] P. Subhash, “IBM HR analytics employee attrition & performance dataset,” Kaggle, 2017. [Online]. Available: https://www.kaggle.com/datasets/pavansubhasht/ibm-hr-analytics-attrition-dataset

View PDF