Hybrid Machine Learning Approach to Employee Effectiveness Evaluation
Karimova Gulshanoy Akmaljon kizi
Fergana State Technical University
Abstract
This thesis presents an electronic employee effectiveness evaluation system based on a hybrid K-Nearest Neighbours (KNN) and Random Forest (RF) classifier with confidence-based routing. Compared with a single-algorithm baseline, the hybrid model raised classification accuracy from 76.2% to 92.8% and halved processing time from 12.4 s to 6.1 s.
Keywords: employee evaluation, KPI, KNN, Random Forest, hybrid classification, AHP, HR analytics
References
1. Breiman L. Random forests // Machine Learning. – 2001. – Vol. 45, No. 1. – P. 5–32.
2. Cover T., Hart P. Nearest neighbor pattern classification // IEEE Transactions on Information Theory. – 1967. – Vol. 13, No. 1. – P. 21–27.
3. Saaty T. L. The Analytic Hierarchy Process. – New York: McGraw-Hill, 1980.
4. DeNisi A. S., Murphy K. R. Performance appraisal and performance management: 100 years of progress? // Journal of Applied Psychology. – 2017. – Vol. 102, No. 3. – P. 421–433.
5. Zokirov S. I., Karimova G. A. Development of a system for forming criteria for determining employee performance (KPI) and methods of calculating the assessment // Engineering Problems and Innovations. – 2025. – No. 3(25).
