About the Project
Stock markets play a pivotal role in economic development and growth of a country. Their performance is regarded as the barometer of economic health and prospects. Stocks are listed and traded on stock exchanges, which provide real-time price information on all securities being traded on that exchange and enable a fair and orderly trading for all market participants. However, financial markets are prone to fraud and different forms of abuse and manipulation whereby market players deliberately interfere with the free and fair operation of the market in order to influence security prices and make unfair profits.
Market abuse damages market integrity and undermines investors’ confidence in financial markets. It is prohibited by financial regulatory authorities in most countries. However, protecting market participants from fraudulent practices and ensuring a fair and orderly market for all investors remains a significant challenge for market abuse regulators. This challenge is further exacerbated by the increase in trading frequency, data volume, variety and velocity as well as cross-market linkages.
The aim of this PhD project is to research and develop data mining and bio-inspired approaches for early detection of irregular trading behaviour and correlated trading patterns across multiple markets. The main focus will be on devising adaptive and scalable anomaly detection methods that are able to identify abnormal trading behaviours in large market data.
Anomaly detection refers to the problem of finding patterns in data that do not conform to expected behaviour. It has been used within diverse application domains where the abnormal patterns are referred to as outliers, novelties, peculiarities etc depending on the application domain. However, the problem of detecting abnormal behaviour is far from unique, and it should be possible to transfer techniques from other domains to market abuse detection where the detection of anomalies translates to significant critical and actionable information.
Please note eligibility requirement:
* Academic excellence of the proposed student i.e. normally an Honours Degree: 1st or 2:1 (or equivalent) or possession of a Masters degree, with merit (or equivalent study at postgraduate level). Applicants may also be accepted on the basis of relevant and substantial practitioner/professional experience.
* Appropriate IELTS score, if required.
For further details of how to apply, entry requirements and the application form, see https://www.northumbria.ac.uk/research/postgraduate-research-degrees/how-to-apply/
Please ensure you quote the advert reference above on your application form.
Funding Notes
The studentship includes a full stipend, paid for three years at RCUK rates (in 2016/17 this is £14,296 pa) and fees (Home/EU £4,350 / International £13,000).
References
1. Ding X., Li Y., Belatreche A., Maguire L. (2015) Novelty Detection Using Level Set Methods. IEEE Transactions on Neural Networks and Learning Systems, 26 (3). pp. 576-588
2. Cao, Y.; Li, Y.; Coleman, S.; Belatreche, A.; McGinnity, T.M. (2015) Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection. IEEE Transactions on Neural Networks and Learning Systems, 26 (2). pp. 318-330
3. Ding X., Li Y., Belatreche A., Maguire L. (2014) "An experimental evaluation of novelty detection methods," Neurocomputing, vol. 135, pp. 313-327.
4. Cao, Y.; Li, Y.; Coleman, S.; Belatreche, A.; McGinnity, T.M., "Detecting Wash Trade in Financial Market Using Digraphs and Dynamic Programming," in IEEE Transactions on Neural Networks and Learning Systems , pp.1-13 doi: 10.1109/TNNLS.2015.2480959 (in press).
5. Wang J, Belatreche A., Maguire L., McGinnity M. (2014) An online supervised learning method for spiking neural networks with adaptive structure. Neurocomputing, 144 . pp. 526-536.
Continue with Facebook
