Evaluation of financial performance using decision tree algorithm method

The purpose of recent study is recognition of the most important financial ratios by which can evaluate company's performance. Therefore the total of accepted companies in stock exchange in Tehran which was active in 1390-1393 are considered as statistical universe of the research through which 102 companies organize the mass of statistical sample based on systematic elimination sampling method. The from the view point of exploratory and functional purpose, the research method is descriptive and interconnection including post –eventual researches. Analysis of data is accomplished by factorial analysis, structural equations modeling and two algorithms by using of CHAID, C&RT software , SPSS, SMARTTPLS, CLEMENTIN decision tree. after explanatory ,factorial analysis, the results of research show that the number of 24 ratios from the total of considered 28 financial ratios is effective in evaluation of company's performance which these ratios are classified in seven categories in terms of weight of each of them from total variance by using of main factor analysis PCA. in next stage, for studying the type of relations and the amount of variant interconnection, confirmatory factorial analysis is performed in structural equations modeling and the main model presented. Finally the result and drawing decision tree indicate that decision tree algorithms are presented the best prediction with the highest accuracy and among the sum of ratios, activity ratio has the most effect on performance evaluation