기계학습 기반의 HR데이터 분석을 통한 퇴직자 예측 모델 개발
Development of Early Retirement Prediction Model through HR Data Analysis Based on Machine Learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
기업에서는 우수 인력의 유출을 방지하고 장기근속을 유도하기 위해 퇴직에 영향을 미치는 요인을 연구한다. 관련된 대부분의 연구는 퇴직자의 주관적 의견에 영향을 받는 설문조사 기반 데이터를 수집하여 분석하거나 국외에서 사용되는 제한된 데이터를 사용하였다. 본 연구에서는 국내 금융IT 기업 채용 전형 과정에서 활용되는 인성평가 데이터 및 재직 중 기록되는 인사평가, HR데이터 등 객관적 데이터를 기반으로 퇴직에 영향을 미치는 요인을 분석하였다. 변수 선택 및 초모수 최적화 과정을 거쳐 다양한 기계학습 모델들의 성능을 비교 후 예측 성능이 우수한 최적의 퇴직자 예측 모델을 개발하였다. 또한 특성 중요도 분석을 통하여 조기 퇴직에 영향을 미치는 주요 요인을 알 수 있었다. 이를 활용하여 체계적인 인사 정책을 수립하고 우수 인력 유지를 위한 관리 노력을 효과적으로 수행한다면 퇴직을 예방하고 장기근속을 유도할 수 있을 것으로 기대된다.
Abstract
Many companies study factors that affect retirement in order to prevent outflow of excellent personnel and induce long-term employment. Most of the related studies collected and analyzed survey-based data influenced by the subjective opinions of retirees, or used limited data used abroad. In this study, factors affecting retirement were analyzed based on objective data such as personality evaluation data used in recruitment process of domestic financial IT companies and personnel evaluation and HR data recorded during employment. After comparing the performance of various machine learning models through variable selection and hyperparameter optimization, an optimal retiree prediction model with excellent predictive performance was developed. In addition, through the feature importance analysis, the main factors affecting early retirement were identified. Using this, it is expected that if a systematic personnel policy is established and management efforts to maintain excellent personnel are effectively carried out, it will be possible to prevent retirement and induce long-term service.
참고문헌 (16)
- W. C. Shin, "ICT-Statistic Analysis-ICT Employment Trend", Korea Information Society Development Institute, 22(4) (2022)
- J. H. KIM, "Expansion of HR Systems for Securing Digital Talents in Banks", Hana Financial Management Research Institute, 13(1), pp.12~12 (2023)
- "Financial Sector Overcomes IT Talent Shortage through 'Infusion' and 'Cultivation'of Digital Talents"[URL]
- "Serious Talent Outflow:84.7% of Companies Experience Early Resignations within One Year!"[URL]
- A Survey of Training, Education, and Intern Personnel Management for 2013 New Employees, "H. B. Lee", Korea Federation of Managers' Associations, 2~6 (2013)
- Y. B. Kim, "Predicting Early Retirees Using Personality Data", Journal of Digital Contents Society, 19(1), pp.141~147 (2018)
- E. J. Lee, "An Exploratory Study on determinants predicting university graduate newcomers’ early turn over", Journal of Corporate Education and Talent Research, 22(1), pp.163~193 (2020)
- J. H. Park, "A study on prediction and prevention of retirement through machine learning based on HR data", Master, pp.2019
- Y. J. Park, "Development of a Resignation Prediction Model using HR Data", Proc. of the Academic Conference on the Korea Institute of Information and Communication Engineering, 25(1), pp.100~103 (2021)
- J. Y. Choi, "Retirement prediction for efficiency of HR management based on machine learning", Master, Department of Data Science, pp.2021
- Hosmer Jr, David W., "Stanley Lemeshow, Rodney X. Sturdivant. Applied logistic regression. vol. 398" (2013), John Wiley & Sons
- Cortes, C, "Support-vector networks", Machine learning, 20(1), pp.273~297 (1995)
- Quinlan, J. Ross, "C4. 5: programs for machine learning" (2014), Elsevier
- Breiman, Leo, "Random forests", Machine learning, 45(1), pp.5~32 (2001)
- Friedman, J. H., "Greedy function approximation: a gradient boosting machine", Annals of statistics, pp.1189~1232 (2001)
- Chen, Tianqi, "Xgboost: A scalable tree boosting system", Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (2016)