P/E Modeling and Prediction of Firms Listed on the Tehran Stock Exchange; a New Approach to Harmony Search Algorithm and Neural Network Hybridization

Abstract

Investors and other contributors to stock exchange need a variety of tools, measures, and information in order to make decisions. One of the most common tools and criteria of decision makers is price-to earnings per share ratio. As a result, investors are in pursuit of ways to have a better assessment and forecast of price and dividends and get the highest returns on their investment. Previous research shows that neural networks have better predictability than statistical models. Thus, Harmony Search algorithm and neural network have been used in this work, since achieving the best forecast is more likely. For this purpose, a sample consisting of 87 companies has been selected from those listed at the Tehran Stock Exchange over a 10-year period (2006-2015). The results show the high accuracy of the designed model that predicts the price-to-earnings ratio at the stock exchange by hybridizing the balanced search algorithm with neural network.