论文信息 - A Human-Friendly MAS for Mining Stock Data

A Human-Friendly MAS for Mining Stock Data

Mining stock data can be beneficial to the participants and researchers in the stock market. However, it is very difficult for a normal trader or researcher to apply data mining techniques to the data on his own due to the complexity involved in the whole data mining process. In this paper, we present a multi-agent system that can help users easily deal with their data mining jobs on stock data. This system guides users to specify their mining tasks by simply specifying the data sets to be mined and selecting pre-defined and/or user-added data mining agents. This approach offers normal traders a practical and flexible solution to mining stock data

Chengqi Zhang | Jiarui Ni

[1] Ashok N. Srivastava,et al. Data Mining: Concepts, Models, Methods, and Algorithms , 2005, J. Comput. Inf. Sci. Eng..

[2] Eugene Fink,et al. Indexing of Compressed Time Series , 2004 .

[3] D. Edwards. Data Mining: Concepts, Models, Methods, and Algorithms , 2003 .

[4] L. Lin,et al. The Applications Of Genetic Algorithms InStock Market Data Mining Optimisation , 2004 .

[5] H. C. Leung,et al. Association Mining System for Financial Ratios and Stock Prices in China and Hong Kong Stock Exchange , 2005, WSTST.

[6] S. Sosvilla‐Rivero,et al. On the profitability of technical trading rules based on artificial neural networks:: Evidence from the Madrid stock market , 2000 .

[7] David Power,et al. The profitability of moving average trading rules in South Asian stock markets , 2001 .

[8] Li Lin,et al. Mining Domain-Driven Correlations in Stock Markets , 2005, Australian Conference on Artificial Intelligence.

[9] James M. Steeley,et al. On the Existence of Visual Technical Patterns in the UK Stock Market , 2003 .