An Online Algorithm for Segmenting Time Series
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Bilateral Bargaining in a One-to-Many Bargaining Setting
AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 3
| Hi-index | 0.00 |
Trading agent concept is very useful for trading strategy design and market mechanism design. In this paper, we introduce the use of trading agent for market surveillance. Market surveillance agents can be developed for market surveillance officers and management teams to present them alerts and indicators of abnormal market movements. In particular, we investigate the strategies for market surveillance agents to detect the impact of company announcements on market movements. This paper examines the performance of segmentation on the time series of trading price and return volatility, respectively. The purpose of segmentation is to detect the turning points of market movements caused by announcements, which are useful to identify the indicators of insider trading. The experimental results indicate that the segmentation on the time series of return volatility outperforms that on the time series of trading price. It is easier to detect the turning points of return volatility than the turning points of trading price. The results will be used to code market surveillance agents for them to monitor abnormal market movements before the disclosure of market sensitive announcements. In this way, the market surveillance agents can assist market surveillance officers with indicators and alerts.