Providing a Model of Earning Transparency with Emphasis on the Criteria of the Govermance System and Performance: An Artificial Intelligence Approach

The objective of this study is to introduce a model for earnings transparency utilizing an artificial intelligence approach within companies listed on the Tehran Stock Exchange (TSE). To investigate this, data from 167 companies spanning the years 2011 to 2018 were analyzed to assess the research hypotheses. A variable selection test, conducted using Lasso s artificial intelligence algorithm, revealed that among the audit committee s independence management system criteria, factors such as the non-executive managers ratio and gender diversity, as well as performance criteria including the ratio of cash holdings in the company, operating profit margin, and accounts receivable ratio, had the most significant impact in elucidating companies earnings transparency. Furthermore, to predict the earnings transparency of these companies in the subsequent year, the LARS algorithm method was employed. The prediction results underscore the high predictive capability of the Lars artificial intelligence algorithm when it comes to forecasting earnings transparency among companies listed on the TSE.