Presenting a Model for Predicting Tax Evasion of Guilds Based on Data Mining Technique

In this research, considering the importance of the topic and the gap in previous researches, a model for predicting tax evasion of guilds based on data mining technique is presented. The analyzed data includes the review of 5600 tax files of all trades with tax codes in Qazvin province during the years 2013-2018. The tax file related to guilds is in five tax groups, including the guild group of owners of official offices, the guild group of real estate consultants, the guild group of catering halls, restaurants and related businesses, the guild group of communication services, and the guild group of showrooms and auto accessories stores and related businesses. The decision tree classification model was used for modeling. The results show that the decision tree model based on the available data is considered a suitable model for prediction. The coverage criterion is 68%, the Kappa criterion is 0.612, which shows the good performance of the modeler. Also, using the Cross Validation technique, the validity of the prediction model was tested in order to more reliably estimate the percentage of modeling performance. The accuracy criterion equal to 67.79% shows the appropriate reliability for the prediction model. The results of this research can be used in formulating operational strategies based on data mining to predict the tax evasion of guilds in the provinces.