An Enterprise Financial Evaluation Model Based on Rough Set theory with Information Entropy

Abstract

Enterprise financial evaluation is an important issue. Rough set is a new technique for data mining domain application. Information Entropy, as a measurement of the average amount of information contained in an information system, is used in the classification of objectives and the analysis of information systems. In this study, establish a financial evaluation model using rough Information entropy approach. Therefore, we firstly define the attribute reduction based on rough set theory. Secondly, we define information entropy. Using this definition, we can easily find the important of attributes. Thirdly, we discuss the reducible indiscernible matrix and decision rule generation. The empirical research which is based on the latest data of Taiwan’s listed company, the result shows that this method is high accurate. Using the unmatched and unbalanced training data and test data, rough set theory with information entropy, shows the best overall prediction accuracy level at 83.4%.