The Application of Artificial Neural Networks in Prediction of TSE Dividend and Price Index (TEDPIX)

Prediction   in financial   affairs especially   in securities   is highly   important.
Investors make wide evaluations  while investing on stocks. One of the main factors considered   by investors during their investments   is to earn returns.  In such circumstances,   a suitable  prediction   model  for stock  returns  will cause the allocation of optimal resources  and efficiency  in capital  market  which are important   issues individually   and  nationally. Recent article addresses the way of predicting stock returns in Tehran Stock Exchange by using Arbitrage multiple  regression  model and artificial neural networks. The variables  of the research  includes 971 samples  of four daily  macro-economic variables namely TSE  Dividend and  Price  Index  (TEDPIX), gold prices, currency exchange rate (Rial/$)  and  the amount of  transactions between Iranian  calendar  years  1381 and 1385 (2002-2006).
To process Arbitrage pricing model, multi-factor regression and to process artificial neural networks (ANNs), Perceptron architecture model with two hidden layers and back-propagation algorithm with sigmoid conversion functions are applied.
To assess the performance of both models, mean absolute deviation (MAD), mean square error (MSE), mean absolute percentage error (MAPE) and root mean square error (RMSE) are utilized.
The findings show the success of both models in predicting cash return index and Tehran Stock  Exchange prices  as  well  as  the  superiority of artificial neural network  over Arbitrage  multiple  model.