نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
In this study, due to the importance of investing in the stock market, the stock price return on the stock exchange is predicted using the short-long term memory recursive neural network (LSTM). The present study is applied in terms of purpose. The statistical population of this study is companies listed on the Tehran Stock Exchange. Among the companies accepted in it, 20 top companies that were present at least in the period of 11/02/2015 to 01/22/2016 and didn't have a significant price gap in that period (because this would lead to a forecast error) They were selected as a sample and their adjusted data (in order to eliminate the gap caused by capital increase and cash dividend distribution) was received from TSECLIENT. That the data of the last 10 days were considered as experimental data and the previous data was considered as educational data. First, the mean and standard deviation of the model prediction error were calculated, which was 602 and 742 for the LSTM recursive neural network model. The results showed that in predicting the stock prices of the top 20 companies on the stock exchange, the predictive power of the LSTM recursive neural network model is statistically appropriate.
کلیدواژهها English