Clustering stock price time series data to generate stock trading recommendations: An empirical study
详细信息 查看全文
- 作者：Binoy B. Naira ; b_binoy@cb.amrita.edu" class="auth_mail" title="E-mail the corresponding author ; P.K. Saravana Kumara ; pksaravanakumar@gmail.com" class="auth_mail" title="E-mail the corresponding author ; N.R. Sakthivelb ; nr_sakthivel@cb.amrita.edu" class="auth_mail" title="E-mail the corresponding author ; U. Vipina ; vipunne@gmail.com" class="auth_mail" title="E-mail the corresponding author
- 关键词：Stock ; Trading ; Recommender ; Clustering ; Time-series
- 刊名：Expert Systems with Applications
- 出版年：2017
- 出版时间：15 March 2017
- 年：2017
- 卷：70
- 期：Complete
- 页码：20-36
- 全文大小：1654 K
文摘
- class="listitem" id="list_celist0001">
- class="label">•
Trading recommender system based on mining historical stock price data is proposed.
- class="label">•
Regression tree and Self Organizing Maps are used to generate temporal clusters.
- class="label">•
Temporal clusters are then used to generate trading recommendations.
- class="label">•
16 recommender system variants are evaluated on US, UK, India and Brazil stocks.
- class="label">•
Proposed recommenders are capable of generating profitable trade recommendations.