데이터 마이닝 모형으로 내부통제 중요한 취약점 탐색

A Material weakness in internal control is defined as a significant deficiency, or combination of significant deficiencies, that results in more than a remote likelihood that a material misstatement of the annual or interim financial statements will not be prevented or detected. This study is to use data mining model for search internal control material weaknesses(ICMW). I examine 3 model of material weaknesses in internal control for 452 firms disclosing material weaknesses from 2004 to 2006 in US. For control firms, I use 417 firms of all Compustat firms with available same SIC and similar to sale that did not disclose to ICMW firms. I use variables of model Cheh, Doyle, Ogneva. If it is training 2004 data and testing 2005 data set, Ogneva model' prediction accuracy highest and Cheh model, Doyle model in the usual order. If it is training 2005 data and testing 2006 data set, Ogneva model' prediction accuracy highest and Doyle model, Cheh model in the usual order. All data set case, Ogneva model' prediction accuracy highest and Doyle model, Cheh model in the usual order. This paper is possible that the major role for determining whether or not a firm has a material weakness in internal control vary among the sample firms. And this study help to future research might attempt to Korean firm related decision making of internal control.