Fitting Multi-Layer Feed Forward Neural Network and Autoregressive Integrated Moving Average for Dhaka Stock Exchange Price Predicting (original) (raw)
Related papers
Forecasting Indian Stock Market Using Artificial Neural Networks
The objective of this research is to predict the next day's opening value of Nifty-100 index of the National Stock Exchange (NSE) using Artificial Neural Networks (ANNs). The ANN is trained using Error Backpropagation Training Algorithm (EBPTA). The multilayer feedforward network is trained using the present day's closing values of seven input parameters which are Gold, Silver, Copper, Crude Oil, Natural Gas and Foreign Exchange (FOREX) rates. In addition to these six rates, the closing value of Nifty-100 index was incorporated as input using Simple Moving Average (SMA) model. The relationship between each input parameter and Nifty-100 index was studied and analyzed using correlation technique. This research proves that Nifty-100 index can be predicted using ANNs.
A Neural Network Model for Predicting Stock Market Prices at the Nairobi Securities Exchange
2014
The Nairobi Securities Exchange (NSE) is a major player in the Kenyan financial sector, dealing with both debt and equity. The entry capital in the equity sector is usually low, hence allowing many ordinary Kenyans to invest in this sector. Investors rely on Stockbrokers to undertake stock trade. Most Stockbrokers use technical, fundamental or time series analysis when advising their clients. However, these methods do not usually guarantee good returns, hence the need to provide Stockbrokers with a substitute predictive tool to guide their decisions. Such a tool can be based on an artificial intelligence (AI) model that trains from available stocks data, gains intelligence and then uses the acquired knowledge for predicting future prices. The research singled out Artificial Neural Network (ANN) as the basis for the model, after considering various algorithms and their suitability for different problem domains. Through experimentation, the project developed an ANN model, based on feedforward multi-layer perceptron (MLP) with error backpropagation. The final model was of configuration 5:21:21:1 i.e. 5 inputs, with two hidden layers each having 21 neurons and 1 output. To test the model, the research developed a prototype, based on C# programming language and tested it on data of daily trades at the NSE compiled in the five-year period 2008-2012. The holdout method was used for training and testing, with 80% data for training and the balance 20% for testing. The results showed that the model was able to predict the future trends of three chosen stocks correctly, with a Mean Absolute Percentage Error (MAPE) of between 0.77% and 1.91%. The performance of the model was also validated by comparative tests with other open sources tools (Neuroph and Encog) on the same NSE data, where the comparative Root Mean Square Error (RMSE) were 1.83 (Prototype), 1.94 (Neuroph) and 2.85 (Encog) on one of the test stocks. The model was tested for applicability to other markets by using data from the New York Stock Exchange, where it achieved a MAPE of between 0.71% and 2.77% on three selected stocks in the same test period. The results showed that ANN-based models can be used to develop low RMSE systems, hence can be used in developing stock market prediction software. This project was done as an ICT for development (ICT4D) initiative.
The Use of Neural Networks in the Prediction of the Stock Exchange of Thailand (SET) index
to financial markets. Many prediction techniques have been reported in stock forecasting. Neural networks are viewed as one of the more suitable techniques. In this study, an experiment on the forecasting of the Stock Exchange of Thailand (SET) was conducted by using feedforward backpropagation neural networks. In the experiment, many combinations of parameters were investigated to identify the right set of parameters for the neural network models in the forecasting of SET. Several global and local factors influencing the Thai stock market were used in developing the models, including the Dow Jones index, Nikkei index, Hang Seng index, gold prices, Minimum Loan Rate (MLR), and the exchange rates of the Thai Baht and the US dollar. Two years' historical data were used to train and test the models. Three suitable neural network models identified by this research are a three layer, a four layer and a five layer neural network. The Mean Absolute Percentage Error (MAPE) of the predictions of each models were 1.
Stock Prediction using Neural Network
Today neural networks have been integrated into most fields and are a very important analytical tool. Neural networks are trained without the restriction of a model to derive parameters and discover relationships, driven and shaped solely by the nature of the data. This has profound implications and applicability to the finance field. Multilayer neural network has been successfully applied to the time series forecasting. Steepest descend, a popular learning algorithm for back propagation network, converges slowly and has the difficulty in determining the network parameters. In fact, artificial neural networks have been widely used for forecasting financial markets. However, such applications to Indian stock markets are scarce. This paper applies neural network models to predict the daily returns of the BSE (Bombay Stock Exchange) Sensex. Multilayer perceptron network is used to build the daily return’s model and the network is trained using Multiple linear regression (MLR) provides a better alternative for weight initialization. It is found that the predictive power of the network model is influenced by the previous day’s return than the first three-day’s inputs. The study shows that satisfactory results can be achieved when applying neural networks to predict the BSE Sensex. However, the proposed Multilayer perceptron network with MLR weight initialization requires a lower computation cost and learns better....
International Journal of Business and Development Studies, 2016
During the recent decades, neural network models have been focused upon by researchers due to their more real performance and on this basis, different types of these models have been used in forecasting. Now, there is a question that which kind of these models has more explanatory power in forecasting the future processes of the stock. In line with this, the present paper made a comparison between static and dynamic neural network models in forecasting (uninvariable) the return of Tehran Stock Exchange (TSE) index in order to find the best model to be used for forecasting this series. The data were collected daily from 26/11/2009 to 17/10/2014. The models examined in this study included two static models (Adaptive Neuro-Fuzzy Inference Systems "ANFIS" and Multilayer Feed-forward Neural Network "MFNN") and a dynamic model (nonlinear neural network autoregressive model "NNAR"). The findings showed that based on the Mean Square Error and Root Mean Square Error criteria, ANFIS model had a much higher forecasting ability compared to other models.
A Stock Market Prediction Model using Artificial Neural Network
Th e use of Neural network s has found a variegated field of applications in the present world. Th is has led to the development of various models for financia l markets and investment. This paper repres ents the idea how to predict share market price us ing Artificial Neural Network with a given input parameters of share market. Artificial Neural Network can remember data of any number of years and it can predict th e feature based on the past data. This paper makes use feed forward ar ch itecture for prediction. The network was trained us ing one year data. It shows a good performance for market prediction. Th e network selected though was not able to predict exact value but it succeeded in prediction the trends of stock market.
Stock Market Data Analysis and Future Stock Prediction using Neural Network
Share market is one of the most unpredictable and place of high interest in the world. There are no significant methods exist to predict the share price. Mainly people use three ways such as fundamental analysis, statistical analysis and machine learning to predict the share price of share market but none of these methods are proved as a consistently acceptable prediction tool. So developing a prediction tool is one of the challenging tasks as share price depends on many influential factor and features. In this paper, we propose a robust method to predict the share rate using neural network based model and compare how it differ with the actual price. For that we collect the share market data of last 6 months of 10 companies of different categories, reduce their high dimensionality using Principal Component Analysis (PCA) so that the Backpropagation neural network will be able to train faster and efficiently and make a comparative analysis between Dhaka Stock Exchange (DSE) algorithm and our method for prediction of next day share price. In order to justify the effectiveness of the system, different test data of companies stock are used to verify the system. We introduce a robust method which can reduce the data dimensionality and predict the price based on artificial neural network.
ANN Model to Predict Stock Prices at Stock Exchange Markets
2014
Stock exchanges are considered major players in financial sectors of many countries. Most Stockbrokers, who execute stock trade, use technical, fundamental or time series analysis in trying to predict stock prices, so as to advise clients. However, these strategies do not usually guarantee good returns because they guide on trends and not the most likely price. It is therefore necessary to explore improved methods of prediction. The research proposes the use of Artificial Neural Network that is feedforward multi-layer perceptron with error backpropagation and develops a model of configuration 5:21:21:1 with 80% training data in 130,000 cycles. The research develops a prototype and tests it on 2008-2012 data from stock markets e.g. Nairobi Securities Exchange and New York Stock Exchange, where prediction results show MAPE of between 0.71% and 2.77%. Validation done with Encog and Neuroph realized comparable results. The model is thus capable of prediction on typical stock markets. Key words: ANN, Neural Networks, Nairobi Securities Exchange, New York Stock Exchange, prediction, learning
FORECASTING STOCK MARKET MOVEMENT: A NEURAL NETWORK APPROACH
Recent researchers approached several techniques to forecast the stock market movement as the motivation for the financial gain. Traditionally, technical analysis approach that forecast stock prices based on historical prices and volume, basic concepts of trends, price patterns and oscillators is commonly used by stock investors to aid investment decisions. In this paper a computational approach called Neural Network is used for the prediction of stock market prices. The training is done with the back propagation algorithm for the data set of the 5 Indian companies. The dataset encompassed the trading days from Aug '04 to Jan '13. The error rate is found for the accuracy prediction in the working platform of MATLAB and is implemented.
Forecasting the Tehran Stock Market by Artificial Neural Network
International Journal of Advanced Computer Science and Applications
One of the most important problems in modern finance is finding efficient ways to summarize and visualize the stock market data to give individuals or institutions useful information about the market behavior for investment decisions. The enormous amount of valuable data generated by the stock market has attracted researchers to explore this problem domain using different methodologies. Potential significant benefits of solving these problems motivated extensive research for years. In this paper, computational data mining methodology was used to predict seven major stock market indexes. Two learning algorithms including Linear Regression and Neural Network Standard feed-forward back prop (FFB) were tested and compared. The models were trained from four years of historical data from March 2007 to February 2011 in order to predict the major stock prices indexes in the Iran (Tehran Stock Exchange). The performance of these prediction models was evaluated using two widely used statistical metrics. We can show that using Neural Network Standard feed-forward back prop (FFB) algorithm resulted in better prediction accuracy. In addition, traditional knowledge shows that a longer training period with more training data could help to build a more accurate prediction model. However, as the stock market in Iran has been highly fluctuating in the past two years, this paper shows that data collected from a closer and shorter period could help to reduce the prediction error for such highly speculated fast changing environment.