Redirigiendo al acceso original de articulo en 21 segundos...
Inicio  /  Algorithms  /  Vol: 14 Par: 8 (2021)  /  Artículo
ARTÍCULO
TITULO

Comparative Analysis of Recurrent Neural Networks in Stock Price Prediction for Different Frequency Domains

Polash Dey    
Emam Hossain    
Md. Ishtiaque Hossain    
Mohammed Armanuzzaman Chowdhury    
Md. Shariful Alam    
Mohammad Shahadat Hossain and Karl Andersson    

Resumen

Investors in the stock market have always been in search of novel and unique techniques so that they can successfully predict stock price movement and make a big profit. However, investors continue to look for improved and new techniques to beat the market instead of old and traditional ones. Therefore, researchers are continuously working to build novel techniques to supply the demand of investors. Different types of recurrent neural networks (RNN) are used in time series analyses, especially in stock price prediction. However, since not all stocks? prices follow the same trend, a single model cannot be used to predict the movement of all types of stock?s price. Therefore, in this research we conducted a comparative analysis of three commonly used RNNs?simple RNN, Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU)?and analyzed their efficiency for stocks having different stock trends and various price ranges and for different time frequencies. We considered three companies? datasets from 30 June 2000 to 21 July 2020. The stocks follow different trends of price movements, with price ranges of $30, $50, and $290 during this period. We also analyzed the performance for one-day, three-day, and five-day time intervals. We compared the performance of RNN, LSTM, and GRU in terms of R2" role="presentation">??2R2 R 2 value, MAE, MAPE, and RMSE metrics. The results show that simple RNN is outperformed by LSTM and GRU because RNN is susceptible to vanishing gradient problems, while the other two models are not. Moreover, GRU produces lesser errors comparing to LSTM. It is also evident from the results that as the time intervals get smaller, the models produce lower errors and higher reliability.

 Artículos similares

       
 
Hamed Taherdoost and Mitra Madanchian    
Blockchain technology has become a powerful disruptive force that upends established ideas in several industries. A fascinating point of convergence is that of blockchain technology and Business Process Management (BPM), where the distributed and immutab... ver más
Revista: Information

 
Marcin Klosok, Daria Gendosz de Carrillo, Piotr Laszczyca, Tomasz Plociniczak, Halina Jedrzejowska-Szypulka and Tomasz Sawczyn    
Revista: Applied Sciences

 
Siarhei Autsou, Karolina Kudelina, Toomas Vaimann, Anton Rassõlkin and Ants Kallaste    
Servomotors have found widespread application in many areas, such as manufacturing, robotics, automation, and others. Thus, the control of servomotors is divided into various principles and methods, leading to a high diversity of control systems. This ar... ver más
Revista: Applied Sciences

 
Kristina Mazur, Mischa Saleh and Mirko Hornung    
Early and rapid environmental assessment of newly developed aircraft concepts is eminent in today?s climate debate. This can shorten the decision-making process and thus accelerate the entry into service of climate-friendly technologies. A holistic appro... ver más
Revista: Aerospace

 
Sideris Kiratsoudis and Vassilis Tsiantos    
Personnel selection stands as a pivotal component within the domain of human resource management, intrinsically tethered to the quality of the workforce at large. In this research endeavor, we introduce the Entropy Synergy Analysis of Multi-Attribute Dec... ver más
Revista: Information