Evaluation of Intelligent and Statistical Prediction Models for Overconfidence of Managers in the Iranian Capital Market Companies

Document Type : Research Paper


1 Faculty Member, Department of Accounting, Sama Technical and Vocational College, Karaj Branch, Islamic Azad University, Karaj, Iran

2 Department of Economics and Accounting, Tehran South Branch, Islamic Azad University, Tehran, Iran



The purpose of the present study was to validate the Adaboost machine learning and probit regression in the prediction of Management's overconfidence at present and in the future. It also compares the predicted models obtained during the years 2012 to 2017. The samples of the research were the companies admitted to the Tehran Stock Exchange, (financial data of 1292 companies/year in total). Data collection in the theoretical part of the study benefitted from the content analysis international research paper in library method and for calculating the data's Excel software was used, and in order to test the research hypotheses, Matlab 2017 and Eviews10.0 were used. The empirical findings demonstrate that The Adaboost's algorithm nonlinear prediction model represents the highest power in learning and prediction (performance of this model) the managerial over-confidence for this year and the following year, proved to be better than the probit regression prediction model.


Main Subjects