Design an integrated optimal hybrid algorithmic trading system with simultaneous multi-price estimation

The design of automated trading systems has increased in various countries, including Iran, recently. The advantage of such systems is the increase in speed and accuracy of trading decisions without emotional interference. Having a model that can simultaneously estimate opening, maximum, minimum, and closing prices is a significant advantage for investors. In this study, using the LSTM neural network, simultaneous estimation of these four prices is performed, and various classification algorithms are used for buying, selling, and holding points to design an optimized algorithmic trading system using a genetic algorithm. To evaluate the proposed model, data from Shapna, Khodro, and Fajr stock markets in Iran from 2012 to 2020 and MATLAB software are used. The results of this research show that the proposed method has a very desirable performance in both simultaneous multi-price estimation and classification of buy, sell, and hold classes. Therefore, it can be considered a very suitable method for automated trading, and a robot based on this method can be designed and implemented in the Iranian stock market for this purpose.