Decision Tree is one of analysis techniques which conducts grouping and prediction into several sub-groups from interested groups. Researcher can easily understand this progress and explain than other techniques. Because Decision Tree is easy technique to see results. This paper uses CART algorithm which is one of data mining technique. It used 273 variables and 70094 data(2010-2011) of working environment survey conducted by Korea Occupational Safety and Health Agency(KOSHA). And then refines this data, uses final 12 variables and 35447 data. To find satisfaction factor in working environment, this page has grouped employee to 3 types (under 30 age, 30 ~ 49age, over 50 age) and analyzed factor. Using CART algorithm, finds the best grouping variables in 155 data. It appeared that ‘comfortable in organization’ and ‘proper reward’ is the best grouping factor.

Abstract
 1. 서론
 2. 연구 대상 및 기존연구방법
  2.1 연구대상 및 기간
  2.2 기존연구방법
 3. 연구방법
  3.1 의사결정나무(Decision Tree)
  3.2 CART 알고리즘
  3.1 분석방법
 4. 분석 결과
  4.1 기초자료분석
  4.2 변수 선택
  4.3 Tree 분석 결과
 5. 결론 및 추후 연구 사항
 6. References
 저 자 소 개

• 이동열(고려대학교 산업시스템공학과) | Dong Ryeol Lee
• 김태호(고려대학교 산업시스템공학과) | Tae Ho Kim
• 이홍철(고려대학교 산업시스템공학과 교수) | HongChul Lee Corresponding author