Abstract—When using the data mining method for stock trading, it is essential to confirm the future stability of the rule found by the data mining method. Even if a rule can explain past data, in situations where the model behind the data changes, there is a risk of loss if an investment is made based on the rule learned using past data. In this study, we analyzed the mechanism behind the high-frequency trading prediction rule proposed in past research and demonstrated its stability. By demonstrating stability, this paper shows that investment using the rule can continue to be the basis for low-risk investment methods in the future.
Index Terms—Data mining, high-frequency trading, stock price prediction, algorithmic trading
Kenichi Yoshida is with Graduate School of Business Science, University of Tsukuba, Otsuka 3-29-1, Bunkyo, Tokyo 112-0012, Japan.
Shigeki Kohda is a Doctoral Candidate of University of Tsukuba, Japan.
Cite: Kenichi Yoshida and Shigeki Kohda, "Stability of Price Prediction Rule for High-Frequency Trading," International Journal of Future Computer and Communication vol. 12, no. 2, pp. 23-26, 2023.
Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0)
Copyright © 2008-2024. International Journal of Future Computer and Communication. All rights reserved.
E-mail: ijfcc@ejournal.net