2009 International Conference on Computational Science and Engineering (2009)
Aug. 29, 2009 to Aug. 31, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSE.2009.281
How to utilize a variety of derivatives so as to obtain positive investment return in different economies concerns the general investors. The present research utilizes a modified APRIORI algorithm called Multi-Dimension Non-Continuous (MDNC), an algorithm by eliminating the limitations imposed by traditional pattern matching of continuous data, to mine the associated rules in the cross-day discrete trading data and find out some valuable information[1 ]. This paper further capitalizes on low cost and tax and trading flexibility characteristics of ETF along with a successful and effective data mining methodology to develop a day-trade strategy with high probability of positive investment return. The current approach outperforms Random Walk Transaction strategy with superior investment return and lower risk level, as evidenced by a 95-percent confidence interval. In other words, the investment strategy proposed by the present research is applicable in any economy situation for positive investment return.
Apriori Algorithm; Association rules; Data Mining; ETF
T. Wen-Chih, C. An-Pin and H. Chiung-Fen, "Application of New A Priori Algorithm MDNC to Exchange Traded Fund," 2009 International Conference on Computational Science and Engineering(CSE), Vancouver, Canada, 2009, pp. 787-794.