Mining Exceptional Activity Patterns in Microstructure Data Yuming Ou, Longbing Cao, Chao Luo and Li Liu Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia {yuming, lbcao, chaoluo, liliu}@it.uts.edu.au Abstract Market Surveillance plays an important role in maintaining market integrity, transparency and fairnesss. The existing trading pattern analysis only focuses on interday data which discloses explicit and high-level market dynamics. In the mean time, the existing market surveillance systems are facing challenges of misuse, mis-disclosure and misdealing of information, announcement and order in one market or crossing multiple markets. Therefore, there is a crucial need to develop workable methods for smart surveillance. To deal with such issues, we propose an innovative methodology — microstructure activity pattern analysis. Based on this methodology, a case study in identifying exceptional microstructure activity patterns is carried out. The experiments on real-life stock data show that microstructure activity pattern analysis opens a new and effective means for crucially understanding and analysing market dynamics. The resulting findings such as exceptional microstructure activity patterns can greatly enhance the learning, detection, adaption and decision-making capability of market surveillance. 1. Introduction In many types of markets such as capital and electricity markets, market surveillance is essential to design market models and business rules, as well as maintain the market integrity, transparency and fairness [1, 2]. The existing market surveillance systems usually rely on surveillance rules for alerting of suspect findings in the market. Most of the surveillance rules are predefined and based on business rules, while some of the surveillance rules may come from statistics and reporting results which can capture more sophisticated abnormal trading behaviour and market movement. These rules play an important role in filtering obvious offences against market business rules, regulation rules, and explicitly exceptional market movements. However, these existing surveillance systems are facing challenges of diversified, dynamic, distributed and cyber-based misuse, mis-disclosure and misdealing of information, announcement and order in one market or crossing multiple markets. Such challenges cannot be handled by the existing systems and techniques usually used in exchanges. In addition, the current price movement and trading pattern analysis mainly focus on interday data such as closing prices. The resulting analytical results are not workable for real-time market surveillance because they cannot catch and filter the microstructure behaviour every second of every day. There is a crucial need to develop breakthrough methodologies and techniques to discover hidden knowledge in the market microstructure data under the increasing financial and trading globalization. In this paper, to deal with the above issues, we propose an innovative methodology — microstructure activity pattern analysis [3], which studies the investor’s behaviours by following and involving market microstructure theories. Investor’s behaviours are recorded in market microstructure data [3] consisting of investor’s actions and interactions with other investors in one market or crossing multiple markets, as well as their embodiment in market dynamics. Microstructure activity pattern analysis aims to identify the investor’s behaviour patterns hidden in microstructure data. The reminder of this paper is organized as follows. Section 2 briefly introduces the market microstructure data. In Section 3 we propose our innovative methodology. A case study in identifying exceptional microstructure activity patterns is carried out in Section 4. We conclude this paper and present our future work in Section 5. 2. Market microstructure and data 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology 978-0-7695-3496-1/08 $25.00 © 2008 IEEE DOI 10.1109/WIIAT.2008.160 880 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology 978-0-7695-3496-1/08 $25.00 © 2008 IEEE DOI 10.1109/WIIAT.2008.160 884