The Relationship between Earnings Variability and Earnings Forecast Using Neural Networks in Companies Listed on Tehran Stock Exchange

The purpose of this research is to investigate the relationship between earnings variabilityand earnings forecast using neural networks in companies listed on Tehran Stock Exchange. Theresearch is of the library and analytical-causal study type, and is based on panel data analysis andneural networks. In this research, financial information of 98 companies from 19 industries inTehran Stock Exchange during the period from 2009 to 2015 has been investigated. Furthermore,software including EXCEL, EVIEWS8, and MINITAB has been used for the analysis of theresults obtained from the study. The findings of the research have demonstrated that there isa significant relationship between earnings variability and earnings forecast. Furthermore, theneural network model performs better than regression in forecasting earnings.