روشی جهت پیش‌بینی قیمت سهام بازار بورس تهران مبتنی بر یادگیری عمیق

در ﺳﺎل ﻫﺎی اﺧﯿﺮ ﺑﺎوﺟﻮد ﺟﺬب ﺣﺪاﮐﺜﺮی ﺳﺮﻣﺎﯾﻪ ﻫﺎی ﺧﺮد و ﮐﻼن ﺑﻪ ﺑﺎزار ﺑﻮرس اوراق ﺑﻬﺎدار در اﯾﺮان ﺳﺮﻣﺎﯾﻪ ﻫﺎی ﺧﺮد و ﮐﻼن، ﻣﺘﺄﺳﻔﺎﻧﻪ ﺑﻪ دﻟﯿﻞ ﻋﺪم اﻃﻼﻋﺎت ﮐﺎﻓﯽ از اﯾﻦ ﺑﺎزار ﭘﺮروﻧﻖ و ﻧﻮﺳﺎﻧﺎت ﻗﯿﻤﺖ آن ﻫﻤﭽﻨﯿﻦ ﮐﻤﺒﻮد ﻧﺮم اﻓﺰارﻫﺎی ﺣﺎوی اﻟﮕﻮرﯾﺘﻢ ﻫﺎی ﭘ ﯿﺶ ﺑﯿﻨ ﯽ ﻗﯿﻤﺖ ﺳﻬﺎم ﺑﻮرس اوراق ﺑﻬﺎدار ﺑﺎ دﻗﺖ ﺑﺎﻻ ﺗﻌﺪاد ﻓﺮاواﻧﯽ از ﺳﻬﺎم داران اﯾﺮاﻧﯽ ﺿﺮر و زﯾﺎن زﯾﺎدی را ﻣﺘﺤﻤﻞ ﺷﺪﻧﺪ. در اﯾﻦ ﺗﺤﻘﯿﻖ ﺑﺮ آن ﺷﺪﯾﻢ ﺗﺎ ﺗﺤﻘﯿﻖ ﻗﺒﻠﯽ ﺧﻮد ﺟﻬﺖ ﭘﯿﺶ ﺑﯿﻨﯽ ﻗﯿﻤﺖ ﺳﻬﺎم ﺑﻮرس اوراق ﺑﻬﺎدار ﺑﺎ اﺳﺘﻔﺎده از ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﺑﺎ دوﻻﯾ ﻪ lstm ﺑﻬﺒﻮد ﺑﺨﺸﯿﺪه و از ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﺗﺮﮐﯿﺒﯽ ﮐﺎﻧﻮﻟﻮﺷﻦ و lstm ﺟﻬﺖ ﭘﯿﺶ ﺑﯿﻨﯽ ﻗﯿﻤﺖ ﺳﻬﺎم ﺑﺮ روی ﻣﺠﻤﻮﻋﻪ داده وب ﻣﻠﺖ از ﺑﺎزار ﺑﻮرس اوراق ﺑﻬﺎدار ﺗﻬﺮان و ﺳﻪ ﻣﺠﻤﻮﻋﻪ داده ﻣﻮﺟﻮد در آن ﺷﺎﻣﻞ آث پ، ﺧﻮدرو و ﺳﺎﺧﺖ ﺑﻬﺮه ﺑﺒﺮﯾﻢ. در اﻧﺘﻬﺎ ﺟﻬﺖ ارزﯾﺎﺑﯽ روش ﭘﯿﺸﻨﻬﺎدی و دو روش دﯾﮕﺮ از ﺳﻪ ﺗﺎﺑﻊ ﺧﻄﺎ، ﺗﺎﺑﻊ ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻊ ﺧﻄﺎ mse ، ﺗﺎﺑﻊ ﻣﯿﺎﻧﮕﯿﻦ ﺧﻄﺎی ﻣﻄﻠﻖ mae و ﺗﺎﺑﻊ ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻊ رﯾﺸﻪ rmse اﺳﺘﻔﺎده ﺷﺪ. ﻧﺘﺎﯾﺞ ﺣﺎﺻﻠﻪ ﻧﺸﺎن داد در ﻣﺠﻤﻮﻋﻪ داده ﻫﺎی ﺑﺰرگ ﺑﺎ ﺗﻌﺪاد داده ﻫﺎی ﺳﻬﺎم ﺑﺎﻻ 1/2 درﺻﺪ ﺑﻬﺘﺮ ﻋﻤﻞ ﻣﯽ ﮐﻨﺪ.

a method for predicting stock prices in tehran stock market based on deep learning

in recent years, due to the profitability of the stock market in iran, small and large investments were attracted to this market, but unfortunately, due to their lack of knowledge of the stock market and price forecasting, a large number of iranians suffered great losses. in this study, we decided to use our previous research, which used a two layer lstm neural network, to strengthen its work and use a combination of convolution and lstm neural networks to predict stock prices on the web nation data set from the stock market. use tehran and its three databases, including asp, car and construction. finally, in order to evaluate the proposed method and the other two methods, three error functions, mean square error function mse , mean absolute error function mae and root mean square function rmse were evaluated. the results showed that it works much better in large datasets with high stock data and leads to fewer errors.