지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 이도길
- 발행연도
- 2022
- 저작권
- 고려대학교 논문은 저작권에 의해 보호받습니다.
이용수33
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
대부분의 기업에서는 우수한 인적 자원의 유출을 방지하기 위해 직원들이 이직 및 퇴사하는 이유를 연구한다. 이에 기업은 직원이 퇴사하기 전에 면담을 하거나 설문조사를 통해서 연구에 필요한 데이터를 얻는다. 하지만 설문조사에서는 직원들이 직장 생활을 하는 데에 불리할 수도 있는 의견을 드러내려고 하지 않아 정확한 결과를 얻기 힘든 것이 현실이다.
본 연구에서는 퇴사자의 주관적 의견에 영향을 받는 설문조사 데이터가 아닌 전공, 교육 수준, 재직 중인 회사 유형 등과 같이 객관적인 데이터를 기준으로 퇴사 예측 모델을 개발하고자 한다.
퇴사 예측 모델을 생성하기 위해 Decision Tree, XGBoost, kNN, SVM을 활용하였으며 각각의 성능을 비교했다. 이 결과, 지금까지 설문조사로 진행되었던 연구에서 파악하지 못한 다양한 요인을 알아낼 수 있었다.
이를 통해 기업이 퇴사 예측 모델을 이용하여 직원이 퇴사하기 전에 미리 이를 인지하고 방지하는 데에 도움을 줄 수 있을 것으로 예상된다.
본 연구에서는 퇴사자의 주관적 의견에 영향을 받는 설문조사 데이터가 아닌 전공, 교육 수준, 재직 중인 회사 유형 등과 같이 객관적인 데이터를 기준으로 퇴사 예측 모델을 개발하고자 한다.
퇴사 예측 모델을 생성하기 위해 Decision Tree, XGBoost, kNN, SVM을 활용하였으며 각각의 성능을 비교했다. 이 결과, 지금까지 설문조사로 진행되었던 연구에서 파악하지 못한 다양한 요인을 알아낼 수 있었다.
이를 통해 기업이 퇴사 예측 모델을 이용하여 직원이 퇴사하기 전에 미리 이를 인지하고 방지하는 데에 도움을 줄 수 있을 것으로 예상된다.
목차
1. 서론·························································································11.1. 연구 배경·········································································11.2. 연구의 목적······································································31.3. 논문의 구성······································································32. 관련 연구··················································································43. 데이터······················································································63.1. 데이터 통계······································································74. 연구 방법················································································165. 실험 결과················································································185.1. Linear Regression을 이용한 Baseline 모델 생성··············205.2. Decision Tree 실험 결과·················································225.3. XGBoost 실험 결과·························································235.4. KNN 실험 결과·······························································245.5. SVM 실험 결과·······························································265.6. 모델 실험 결과································································276. 결과 해석················································································287. 결론························································································308. 참고문헌··················································································31
최근 본 자료
댓글(0)
0