Most models for the time series of stock prices have centered on autoregressive (AR) processes. Traditionally, fundamental Box-Jenkins analysis have been the mainstream methodology used to develop time series models. We briefly describe developing a classical AR model for stock price forecasting. Then a fuzzy regression model is introduced. Following this description, an artificial fuzzy neural...

Linear multiple kernel learning model has been used for predicting financial time series. However, ℓ(1)-norm multiple support vector regression is rarely observed to outperform trivial baselines in practical applications. To allow for robust kernel mixtures that generalize well, we adopt ℓ(p)-norm multiple kernel support vector regression (1 ≤ p < ∞) as a stock price prediction model. The optim...

Stock patterns are those that occur frequently in stock time series, containing valuable forecasting information. In this paper, an approach to extract patterns and features from stock price time series is introduced. Thereafter, we employ two ANN-based methods to conduct clustering analyses upon the extracted samples, which are the self-organizing map (SOM) and the competitive learning. Beside...

Accurate stock trend prediction is a difficult job because various intricate and complex factors affect changes in price, trading volume and trends of a stock market. On a macro scale, the factors could be the overall global economic environment, industry trends, individual economic environment (business operation and competitors’ development), the amount of floating capital in the market, etc....

This paper presents a forecasting approach, in which stock price direction in the next day can be predicted based on nonlinear probability models and technical indicators. The proposed method incorporates various indicators into Logit, Probit, and Extreme Value models permitting a decision maker to forecast the direction of stock movements more efficiently. The utilized indicators include Movin...

The stock market is very volatile, so the change of price also widely concerned by investors. In this paper, a new forecasting model based on Quantum Particle Swarm Optimization(QPSO) , Bee Colony Optimization Algorithm(QABC) and Fruit Fly Algorithm (QFOA) proposed. three methods all use BP neural network to adjust parameters particle swarm, bee colony Drosophila reach optimal parameters. Takin...

Stock market represents an essential part of the economy in the Middle East, it is significant for shareholders and investors to estimate the stock price and select the best trading opportunity accurately in advance. This paper utilizes artificial neural network in the modeling of stock market exchange prices. The network was trained using supervised learning. Simulation was conducted for seven...