A Novel Data Mining Algorithm based on BP Neural Network and Its Applications on Stock Price Prediction

Abstract

Abstract.As an indispensable part in financial industry, stock investment has gradually become more and more important in people's life. The major fluctuation in stock market directly affects the stability of financial markets and the healthy development of the economy. The successful stock price and trend prediction will help investors to yield profit and provide timely and reasonable guidance to market regulators. Therefore, how to forecast stock market is a crucial and worthy topic in financial area. Neural network simulated how brain functions, can automatically extract features from the historical data and related information to predicate future trend, with the primary characteristics of self-organization and adaption. Therefore, neural network is suitable for processing prediction in the field of nonlinear time series. This paper presents a novel data mining algorithm based on the BP neural network and its applications on stock price prediction. Taking improving the efficiency of the traditional back propagation network, we revise the perspective error, and modify incentive function and the adaptive learning rate in order to avoid the local minimum and decrease training time. Moreover, to eliminate the influences caused by noisy data, we combine the fuzzy rough set theory to pre-process the original data. The experimental result verifies feasibility of our model, without the local minimum and slow convergence speed, compared to the other state-of-the-art approaches. Therefore, our algorithm on the predications of the exact stock price value and future trend are applicable and satisfactory.

Triangulation between Bernoulli Distribution and Laplacian Autoregressive Model to Predict Probability of Increase in Stock Price

“…The main contribution of this research lies in providing information, especially potential investors before buying and selling stocks so that potential investors do not lose money. This is reinforced by the results of research that stock market predictions are an important and valuable topic in finance [4]. The novelty in this study is the use of the triangulation method so that the accuracy of the results is better.…”

“…Stocks are proof of ownership of a company. Several researchers have conducted research on the topic of stocks, for example: [4], [5], [6], and [7]. In [4], the authors present a new data mining algorithm based on back propagation neural networks and its application to stock price predictions.…”

“…Several researchers have conducted research on the topic of stocks, for example: [4], [5], [6], and [7]. In [4], the authors present a new data mining algorithm based on back propagation neural networks and its application to stock price predictions. To improve the efficiency of the traditional back propagation network, the authors do this by revising the perspective error, and modifying the incentive function and adaptive learning speed so as to avoid local minimums and reduce training time [4].…”

“…In [4], the authors present a new data mining algorithm based on back propagation neural networks and its application to stock price predictions. To improve the efficiency of the traditional back propagation network, the authors do this by revising the perspective error, and modifying the incentive function and adaptive learning speed so as to avoid local minimums and reduce training time [4]. Whereas in [5], the authors propose a decomposition-forecast-synthesis (DFS) model in predicting stock prices.…”