Adaptive hidden Markov model with anomaly states for price manipulation detection
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96989441
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2014.2315042
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 318
- Volume
- 26
- Issue
- 2
- ISSN
- 2162-237X
- Open access status
- Out of scope for open access requirements
- Month of publication
- April
- Year of publication
- 2014
- URL
-
http://dx.doi.org/10.1109/TNNLS.2014.2315042
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
C - Cybersecurity, privacy and human centred computing
- Citation count
- 34
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper tackles the critical problem of detecting anomalies indicating stock manipulation in capital markets based on a collaboration with five financial companies (including two Fortune 500). The work has been used as a benchmark by other authors (e.g., https://doi.org/10.1109/ACCESS.2020.3011590 and https://doi.org/10.1016/j.neucom.2019.03.006), and has been cited by anomaly detection work from other fields including Chemical Engineering (e.g., https://doi.org/10.1016/j.ces.2019.01.060). The work led to the award of an Innovate UK project (KTP10279, Li with Activequote ltd.) focusing on improving the rate of customer conversion.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -