In recent years, due to the technological improvements in computers’ hardware and enhancements in the machine learning techniques, there are two increasing approaches for problem-solving as the use of “Big Data” and “Parallel Processing”. Especially with the emergence of Deep Learning algorithms which can be executed parallelly on multi-core computing devices such as GPUs and CPUs, lots of real-world problems are resolved with these approaches. One of the most critical application areas in the Financial Market especially sits on Stock Markets. In this area, the aim is to try to predict the future value of a specific stock by looking at its previous financial data on the exchange process in the market. In this paper, we proposed a system that uses a Deep Learning based approach for training and constructing a knowledge base on a specific stock such as “IBM”. We get time series values of the stock from the New York Stock Exchange which starts from 1968 up to 2018. Experimental results showed that this approach produces very good forecasting for specific stocks.
- deep learning,
- big data,
- stock exchange
- Deep learning,
- Biological system modeling,
- Big Data,
- Stock markets,
- Machine learning algorithms
The most important role of investors is to analyze the movements of financial markets and to make an accurate prediction. For decades, investors have tried to use some methodologies and techniques for increasing profit. In the analysis of these movements was examined under two categories. Firstly, technical analysis can be explained as predicting targetable price movements based on past price movements. This type of analysis is the method of analysis used in the markets where volatility is high, such as FOREX market (Foreign Exchange Market). Secondly, the fundamental analysis method predicts the expected price movements of financial data based on economic, environmental, political, and other factors as well as statistical data in the analysis. On account of the use of increasing and developing technology, the number of operations performed instantaneously increased in a direct proportion. Attempts to estimate stock prices along with the increasing number of transactions have also been the subject of research for a long time, and some methods have been proposed in various academic researches. However, results show that no method alone has achieved the desired success. In order to assist investors in general, the desired systems should advise on the best possible action as soon as possible. Therefore, some decision support system which is trained with some learning mechanism is a good solution for this.
In the computer science field, there are many works on this subject which use different learning approach for the training of the system, lots of them focused on the use of the neural network approach. However, in recent years, with the extended use of powerful computers and being able to access a huge size of data, Deep Learning is one of the most attractive research areas for using different real-world application areas. Recurrent neural networks (RNN), which is one of the important deep learning models, has proven its strength in sequential data such as time series in many academic studies. Based on this knowledge, we have reached the best results with Long Short-Term memory which is one of the most successful RNNs architecture. Therefore, we used LSTM in our work. The purpose of this project is to use the stock market data we have in order to estimate the high-volume financial time series on deep learning.
Making accurate forecasting in stock markets is a very challenging task due to the nonlinearity of the financial time series. Some researchers in this area say that stock prices behave in a random walk manner. However, technical analysts insist that future prices can be predicted somehow by considering some current values. In this paper, as one of the deep learning approaches, the LSTM network is applied to a large-scale stock market NYSE, NASDAQ, and NYSE MKT, ranging from January 2, 1968, to April 09, 2018, for predicting the future values. With the use of LSTM architectures, some hidden dynamics of the market can be captured, and efficient predictions can be possible. The proposed model results in an acceptable root mean square error (RMSE) value as 0.04. As future work, we aimed to take into consideration some new features for making more accurate predictions. Additionally, some parameter values can be set by using some optimization algorithms to increase the efficiency of the system. Finally, for using a huge parallelization, system execution can be transferred to GPU structures as mentioned in .
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
FULL Paper PDF file:Deep Learning-Based Forecasting in Stock Market with Big Data Analytics
Deep Learning-Based Forecasting in Stock Market with Big Data Analytics
2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), Istanbul, Turkey, 2019, pp. 1-4
PDF reference and original file: Click here