The Optimal Multi-layer Structure of Backpropagation Networks (original) (raw)
Related papers
A Comparative Study Of Backpropagation Algorithms In Financial Prediction
International Journal of Computer Science, Engineering and Applications, 2011
Stock market price index prediction is a challenging task for investors and scholars. Artificial neural networks have been widely employed to predict financial stock market levels thanks to their ability to model nonlinear functions. The accuracy of backpropagation neural networks trained with different heuristic and numerical algorithms is measured for comparison purpose. It is found that numerical algorithm outperform heuristic techniques.
Application of artificial neural networks with backpropagation technique in the financial data
IOP Conference Series: Materials Science and Engineering, 2017
The propensity of applying neural networks has been proliferated in multiple disciplines for research activities since the past recent decades because of its powerful control over regulatory parameters for pattern recognition and classification. It is also being widely applied for forecasting in the numerous divisions. Since financial data have been readily available due to the involvement of computers and computing systems in the stock market premises throughout the world, researchers have also developed numerous techniques and algorithms to analyze the data from this sector. In this paper, we have applied neural network with backpropagation technique to find the data pattern from finance section and prediction for stock values as well.
Modified neural network algorithms for predicting trading signals of stock market indices
Journal of Applied Mathematics and Decision Sciences, 2009
The aim of this paper is to present modified neural network algorithms to predict whether it is best to buy, hold, or sell shares trading signals of stock market indices. Most commonly used classification techniques are not successful in predicting trading signals when the distribution of the actual trading signals, among these three classes, is imbalanced. The modified network algorithms are based on the structure of feedforward neural networks and a modified Ordinary Least Squares OLSs error function. An adjustment relating to the contribution from the historical data used for training the networks and penalisation of incorrectly classified trading signals were accounted for, when modifying the OLS function. A global optimization algorithm was employed to train these networks. These algorithms were employed to predict the trading signals of the Australian All Ordinary Index. The algorithms with the modified error functions introduced by this study produced better predictions.
Efficient prediction of stock market indices using adaptive neural network
2012
This paper presents a neural network model for financial time series prediction of leading Indian stock market indices. Financial time-series data are usually non-stationary and volatile in nature. This model employs Multilayer Feedforward (MLFF) network with Backpropagation (BP) learning. In this article we discuss the modeling of the Indian stock market (price index) data using artificial neural network (ANN). We study the efficacy of ANN in modeling the Bombay Stock Exchange (BSE), Reliance and Oracle data set on closing values. The root mean square error (RMSE) and mean absolute error (MAE) are chosen as indicators of performance of the network. The backpropagation learning algorithm selects a training example, makes a forward and a backward pass, and then repeats until algorithm converges satisfying a pre-specified mean squared error value. The results show the potential of the system as a tool for making stock price prediction.
This paper presents a study of Artificial Neural Network (ANN) and Bayesian Network (BN) for use in stock index prediction. The data from Nigerian Stock Exchange (NSE) market are applied as a case study. Based on the rescaled range analysis, the neural network was used to capture the relationship in terms of weights between the technical indicators derived from the NSE data and levels of the index. The BayesNet Classifier was based on discretizing the numeric attributes into distinct ranges from where the conditional probability was calculated, stored in the Conditional Probability Table (CPT) and the new instance were classified. The performance evaluation carried out showed results of 59.38% for ANN and 78.13% for BN in terms of predictive power of the networks. The result also showed that Bayesian Network has better performance than ANN when it comes to predicting short period of time; and that useful prediction can be made for All Share index of NSE stock market without the use of extensive market data.
Academy of Information and Management Sciences Journal, 2008
In this study, we forecast Korean Stock Price Index using historical weekly KOSPI data and three forecasting models such as back-propagation neural network model (BPNN), a Bayesian Chiao's model (BC), and a seasonal autoregressive integrated moving average model (SARIMA). KOSPI are forecasted over three different periods. (i.e., short-term, mid-term, & long-term) The performance of the forecasting models is measured by the forecast accuracy metrics such as absolute forecasting errors and square forecasting errors of each model. The findings are as follows: first, between BPNN and BC, BPNN performs better than BC for mid term and long term forecasting, while BC performs better than BPNN for the short term forecasting. The second, between BPNN and SARIMA, SARIMA performs better than BPNN for mid term and long term forecasting, while BPNN does better than SARIMA the short term forecasting. Between SARIMA and BC, SARIMA performs better than BC for mid term and long term forecasting, while the other way around is true the short term forecasting. In sum, the SARIMA performs best among the three models tested for mid term and long term forecasting, while BC performs best for the short term forecasting.
Forecasting stock indices with back propagation neural network
Expert Systems with Applications, 2011
Stock prices as time series are non-stationary and highly-noisy due to the fact that stock markets are affected by a variety of factors. Predicting stock price or index with the noisy data directly is usually subject to large errors. In this paper, we propose a new approach to forecasting the stock prices via the Wavelet De-noising-based Back Propagation (WDBP) neural network. An effective algorithm for predicting the stock prices is developed. The monthly closing price data with the Shanghai Composite Index from January 1993 to December 2009 are used to illustrate the application of the WDBP neural network based algorithm in predicting the stock index. To show the advantage of this new approach for stock index forecast, the WDBP neural network is compared with the single Back Propagation (BP) neural network using the real data set.
Predicting the Direction of Stock Markets Employing Back Propagation in Neural Networks
Stock Market prediction is a category of time series prediction which extremely challenging due to the dependence of stock prices on several financial, socioeconomic and political parameters etc. Moreover, small inaccuracies in stock market price predictions may result in huge losses to firms which use stock market price prediction results for financial analysis and investments. Off late, artificial intelligence and machine learning based techniques are being used widely for stock market prediction due to relatively higher accuracy compared to conventional statistical techniques. The proposed work employs the steepest descent based scaled conjugate gradient (SCG) algorithm along with the data pre-processing using the discrete wavelet transform (DWT) for stock market prediction. It has been shown that the proposed system attains lesser mean square percentage error compared to previously existing technique.
Optimizing the Architecture of Artificial Neural Networks in Predicting Indian Stock Prices
International Journal of Computing Algorithm, 2014
In forecasting, the design of an Artificial Neural Network (ANN) is a non-trivial task and choices incoherent with the problem could lead to instability of the network. So a Genetic Algorithm (GA) approach is used to find an optimal topology for the prediction. This paper presents a novel approach to Optimization of ANN topology that uses GA for the forecasting of Indian Stock Prices under Bombay Stock Exchange. After determining the optimum network determined by GA, forecasting of the stock prices is found by implementing MATLAB tool. The paper is organized as follows. The first Sectiondeals with the introduction to Genetic Algorithms; Section two reviews the literature on the optimization of neural network architectures and applications of genetic algorithms in doing so. Section three gives the proposed approach in the optimization of neural network architectures. Section four presents the experimental results by the methodology described in section three and followed by results and conclusion.
Neural network model selection for financial time series prediction
Computational Statistics, 2001
Can neural network model selection be guided by statistical procedures such as hypothesis tests, information criteria and cross-validation? Recently, Anders and Kom (1999) proposed five neural network model specification strategies based on different statistical procedures. In this paper, we use and adapt the Anders-Koru framework to find appropriate neural network models for financial time series prediction. The most important new issue in this context is the specification of IIII. dynamic structure of the models, i.e. the selection of the lagged values of the input time series. A linear model is built with full dynamic structure, then its possihl« nonlinear extensions are tested using a statistical procedure inspired by thl' Anders-Kom approach. Promising results are obtained with an application 10 predict the monthly time series of mortgage loans purchased in The Netherlands.