پیش بینی بازار سهام NSE با استفاده از مدل های یادگیری عمیق
Abstract
1- Introduction
2- ARTIFICIAL NEURAL NETWORK
3- Methodology
4- RESULTS AND DISCUSSION
5- CONCLUSION
References
Abstract
The neural network, one of the intelligent data mining technique that has been used by researchers in various areas for the past 10 years. Prediction and analysis of stock market data have got an important role in today’s economy. The various algorithms used for forecasting can be categorized into linear (AR, MA, ARIMA, ARMA) and non-linear models (ARCH, GARCH, Neural Network). In this paper, we are using four types of deep learning architectures i.e Multilayer Perceptron (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for predicting the stock price of a company based on the historical prices available. Here we are using day-wise closing price of two different stock markets, National Stock Exchange (NSE) of India and New York Stock Exchange (NYSE). The network was trained with the stock price of a single company from NSE and predicted for five different companies from both NSE and NYSE. It has been observed that CNN is outperforming the other models. The network was able to predict for NYSE even though it was trained with NSE data. This was possible because both the stock markets share some common inner dynamics. The results obtained were com- pared with ARIMA model and it has been observed that the neural networks are outperforming the existing linear model (ARIMA).
Introduction
Stock market is a place where shares or stocks of a firm are traded. It can be split into two components: • primary market • secondary
market Primarymarket is where new issues are introduced to the market through Initial Public Offerings. Secondary market is where investors trade securities that they already own. Stock market is having a highly fluctuating and non-linear time series data. A time series is a set of data measured over time to acquire the status of some activity [6]. Linear models like AR, ARMA, ARIMA [9][10] have been used for stock market forecasting. The only problem with these models are, that they work only for a particular time series data, i.e the model identified for a particular company won’t perform well for another. Due to the equivocal and unforeseeable nature of stock market, stock market forecasting takes higher risk compared to other sectors. It is one of the most important reason for the difficulty in stock market prediction. Here is where the application of deep-learning models in financial [4] forecasting comes in. Deep neural network got its name due to the use of neural network architecture in DL models. It is also called as ANN. ANNs are good approximators and they are capable to learn and generalize from experience. Practical application of ANN in forecasting problems is very successful due to the following characteristics:
• ANN’s are good function approximators, so the input and output relationship can be examined by them even if the data set is very complex. • ANN’s can identify new test samples even if they have not been used during the training of network.