A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression

Abstract

AbstractsStock price prediction has attracted much attention from both practitioners and researchers. However, most studies in this area ignored the non-stationary nature of stock price series. That is, stock price series do not exhibit identical statistical properties at each point of time. As a result, the relationships between stock price series and their predictors are quite dynamic. It is challenging for any single artificial technique to effectively address this problematic characteristics in stock price series.One potential solution is to hybridize different artificial techniques. Towards this end, this study employs a two-stage architecture for better stock price prediction.Specifically, the self-organizing map (SOM) is first used to decompose the whole input space into regions where data points with similar statistical distributions are grouped together, so as to contain and capture the non-stationary property of financial series. After decomposing heterogeneous data points into several homogenous regions, support vector regression (SVR) is applied to forecast financial indices. The proposed technique is empirically tested using stock price series from seven major financial markets. The results show that the performance of stock price prediction can be 2 significantly enhanced by using the two-stage architecture in comparison with a single SVR model.

An Improved Hybrid Algorithm Based on PSO and BP for Stock Price Forecasting

“…In fact, even if there are a large sample data, but it does not necessarily find rule, even if there is a statistical rule, but it is also not a typical. The other is the artificial intelligence technique such as artificial neural network (ANN) [3][4][5], genetic algorithm (GA) [6,7], and many hybrid intelligent algorithms [8][9][10][11]. The hybrid intelligent algorithms have more flexibility to solve the complex models, so more and more researchers tend to use them to deal with forecasting problems.…”

Taxonomy of Marketing Strategies Using Bank Customers’ Clustering

“…Wei et al (2012) adopted self-organizing maps (SOM) methodology in order to extend the RFM model. SOM is a neural network method which can be used for clustering problems, visualization, and market screening (Fish & Ruby, 2009;Hanafizadeh & Mirzazadeh, 2011;Hsu et al, 2009;Hung & Tsai, 2008;Kiang & Fisher, 2008;Wang, 2001;Wei et al, 2012). SOM also has the advantage of automatically detecting strong features in large data sets (Wei et al, 2012).…”

Hybrid Corporate Performance Prediction Model Considering Technical Capability

“…At the same time, the advancement of data processing technology and machine-learning algorithms have resulted in efforts to develop sustainable quantitative prediction models and to update new training data in a simple manner. For example, the management and economic sectors use machine-learning algorithms such as artificial neural networks and decision trees to produce quantitative predictions [1,[3][4][5][6][7]. However, most related studies establish prediction models using financial indicators that have been deduced from financial information, excluding technological information, from which they predict performance and stock prices [1,3,4].…”

“…Many studies have attempted to predict corporate performance, stock prices, or economic trends in order to enhance the profitability of investments and the efficiency of mergers and acquisitions (M&A) [1][2][3][4][5][6][7]. Such studies commonly analyze the market flow and financial information (e.g., financial statements) of companies to predict their performance [2,6,7].…”

“…For example, the management and economic sectors use machine-learning algorithms such as artificial neural networks and decision trees to produce quantitative predictions [1,[3][4][5][6][7]. However, most related studies establish prediction models using financial indicators that have been deduced from financial information, excluding technological information, from which they predict performance and stock prices [1,3,4]. Thus, excluding a technology-intensive company's technological capabilities from model training limits the model's ability to predict the company's performance or to establish a sustainable managerial strategy.…”