چکیده:
Discussions about forecasting Stock returns in developed countries has long been regarded as one of the most interesting scientific topics.However,due to many problems,the correct prediction of stock returns has remained a matter of strengthTtherefore,the researcher seeks to provide an accurate,practical and effective model for predicting stock returns for investors.The statistics sampel of research is consist of 138 active companies in Tehran Stock Exchange from 2008 to 2017 wich are selected by the systematic removal method . ANFIS,MGGP, regresion and neural network and different statistics tests are used for data analysis. For impelement of these techniques MATLAB and GenXproTools software are used respectively.The result of the study showed that in oreder to predict stock returns.the use of a meta –heuristic Hybrid models is more accurate and faster than other meta huristic models.Because ,first the most optimal input variables are selected through the ANFIS technique and then predicted using theMGG meta heuristic model.Therefore,due to the correct choice of input variables,predicting stock returns is both more accurate and faster.In addition ,the mathematical model is used to predict.
خلاصه ماشینی:
Therefore, it can be stated that using a neural network can only provide a single number as a prediction to the researcher, but these methods are not capable of providing a mathematical model for the dependent variable (stock return) based on the independent variables (accounting, financial variables).
The research literature related to stock return prediction shows that the use of artificial intelligence (meta-heuristic) methods such as the Adaptive Neuro-Fuzzy Inference System 5 (ANFIS) in the field of 391 accounting has not been used to determine the independent variables that have the greatest effect on stock return prediction.
Furthermore, the use of genetic methods such as Multi-Gene Genetic Programming 6 (MGGP) in stock return prediction, which can overcome the black box weakness present in traditional artificial intelligence methods like neural networks, has not been seen in previous research; all of this led the researcher to provide a model by integrating two methods: the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Multi-Gene Genetic Programming (MGGP), so that it is both more accurate and effective in stock return prediction in less time.
This research intends to investigate the effect of using the Adaptive Neuro-Fuzzy Inference System (ANFIS) method, not as a prediction tool, but as an intelligent tool in determining input independent variables on modeling speed and model accuracy in stock return prediction, through the results obtained from comparing two models, ANFIS-MGGP, with the pure MGGP model and the multilayer perceptron neural network model 7.
(
, 
, 
)
