Evaluating Accuracies of a Trading Rule Mining Method Based on Temporal Pattern Extraction
Abstract
In this paper, we present an evaluation of accuracies of temporal rules obtained from the integrated temporal data mining environment using trading dataset from the Japanese stock market. Temporal data mining is one of key issues to get useful knowledge from databases. However, users often face on difficulties during such temporal data mining process for data pre-processing method selection/construction, mining algorithm selection, and post-processing to refine the data mining process. To get rules that are more valuable for domain experts from a temporal data mining process, we have designed an environment, which integrates temporal pattern extraction methods, rule induction methods and rule evaluation methods with visual human-system interface. Then, we have done a case study to mine temporal rules from a Japanese stock market database for trading. The result shows the availability to find out useful trading rules based on temporal pattern extraction.
Cite
Text
Abe et al. "Evaluating Accuracies of a Trading Rule Mining Method Based on Temporal Pattern Extraction." European Conference on Machine Learning, 2007. doi:10.1007/978-3-540-68416-9_6Markdown
[Abe et al. "Evaluating Accuracies of a Trading Rule Mining Method Based on Temporal Pattern Extraction." European Conference on Machine Learning, 2007.](https://mlanthology.org/ecmlpkdd/2007/abe2007ecml-evaluating/) doi:10.1007/978-3-540-68416-9_6BibTeX
@inproceedings{abe2007ecml-evaluating,
title = {{Evaluating Accuracies of a Trading Rule Mining Method Based on Temporal Pattern Extraction}},
author = {Abe, Hidenao and Hirabayashi, Satoru and Ohsaki, Miho and Yamaguchi, Takahira},
booktitle = {European Conference on Machine Learning},
year = {2007},
pages = {72-81},
doi = {10.1007/978-3-540-68416-9_6},
url = {https://mlanthology.org/ecmlpkdd/2007/abe2007ecml-evaluating/}
}