Applying Data Mining Technique to Analyze Sequential Patterns in the Stock Market in Taiwan

• Main Authors: Ming-Wei Yeh, 葉明威
• Other Authors: T.P. Liang
• Format: Others
• Language: zh-TW
• Published: 2003
• Online Access: http://ndltd.ncl.edu.tw/handle/17971725754915840294

碩士 === 國立中山大學 === 資訊管理學系研究所 === 91 === Our research adopts data mining technique to analyze stock market and build the analysis model, from the historical data of the stock market, to assist investment decision. The performance of the stock market is the collection of all individuals’ decisions, taking the Taiwan’s stock market for instance, there is a phenomenon that all the prices of the stocks in the same industry will raise in turn, and a lot of corporations and investors will invest some industry more actively and then invest another industry sequentially according the strategies of the corporations or other reasons. Besides, based on the theory of recurring prosperity, investors and corporations will decide the target of investment by the characteristics of the industry and the status of the prosperity and show a recurring investment strategy. The phenomenon of sequential investment can be discovered by using Data Mining technique, especially the Sequential Pattern Analysis in Data Mining technique. The Sequential Pattern Analysis is used to analyze the sequential relation between two things, and this technique has been improved greatly in recent days. Using this technique to analyze the behavior of stock market can be a whole new research topic. The object of this research is to generalize a sequential pattern of the investment in Taiwan’s stock market. Based on the history transaction data of Taiwan’s stock market, we mine for the sequential pattern of different stocks in Taiwan’s stock market and then build the behavior model of Taiwan’s stock market in order to help the stock investors to make the correct decisions.