Implementing machine learning methods in the prediction of the financial constraints of the companies listed on Tehran’s stock exchange

Abstract One of the main issues in the prediction of financial constraints is the choice of predictor variables. In this study we used machine learning Gussian process and radial neural network to predict the financial constraints. The statistical society consists of 208 companies from 2011 to 2017 and considering the availability of the information all the companies were analyzed as the statistical samples. The results of this study show that machine learning methods can predict the financial constraints of the companies listed on Tehran’s stock exchange. Therefore the main hypothesis of this study is confirmed and machine learning methods are an effective method to predict the financial constraints. Also the results of this study show that the value of the company, the ratio of operating cash to assets, financial leverage, return on assets and the percentage of institutional owners are the main variables in predicting the financial constraints. Key words: financial constraint, machine learning method, radial neural network, Gussian process regression