Review and Prediction Relation between Share Return and Market Variables by using of Artificial Neural Networks

With respect to the importance of return in investment studies, estimation its relation with market variables is necessary and important problems. Time changes of return, inefficiency studies performed and presence of effective factors on share retune rate are caused development modern and intelligent methods in estimation and evaluation of share return in stock companies. Aim of this research is prediction of share return by using of market variables with artificial neural Network approach. Independent variables in this research are market variables (price to book value, selling price to price, price to operational cash flow, price to earning) and dependent variable is share return, thereby market variables gathered for 100 stock companies in during 5 years. The obtained outputs from estimation of the artificial neural networks and results obtained from estimation, using of this method with evaluation scales are (MAE = 0.21 and RMSE -0.064, R2=0.12). Concerning random amount (50%) and comparing it with R2=0.12, we found that there is no meaning relation between the associated variables and share return, however, such network has the least error than other Networks (MAE=0.21, RMSE = 0.64).

Future return, Future share return prediction, Artificial Neural Networks, Market variables.