생존분석을 이용한 기술보증기업의 부실예측모형에 관한 연구: 기술평가 자료를 중심으로 = A Study on the Corporate Insolvency Prediction Model of Technology Guaranteed Firms Using Survival Analysis

다국어 초록 (Multilingual Abstract)

This study figures out the factors that affects survival and estimate survival time of small and medium-sized enterprises by using technology rating data for the companies guaranteed by Korea Technology Finance Corporation (KOTEC). In addition, this study develops corporate bankruptcy prediction model using estimated survival time and conduct a comparative study on logit model. To serve the purposes, the researcher uses Cox proportional hazards (Cox PH) model and accelerated failure time (AFT) model. The 17,210 guaranteed companies that assessed from July 1st in 2005 to December 31st in 2009 are selected as samples (16,332 censored data and 878 bankruptcy data). The survival time is computed with random censoring (Type III) from July in 2005 as a starting point. The results of the analysis show that Cox proportional hazards model is useful to understand which technology rating items are meaningful to company`s survival and how much they affect it. And AFT model shows comparable result with respect to logit model for binary classification because area under receiver operating characteristic (AUROC) of AFT model is a little bit wider than logit model. Therefore, AFT model is expected to act as a bankruptcy prediction model in the future. It is considered that these results will provide valuable knowledge for practitioners to find and manage the significant items for survival of the guaranteed companies through future technology rating.