Skip to content
All library documents

Detecting Market Abuse with Trader Profiles and News Timing

Article Quant Q&A · Author: Mehness
Read the original

Summary

The document gathers suggestions for quantitative investigation of suspicious stock trading, including spoofing and possible information asymmetry. One proposed method builds behavioral attributes for each trader, such as trading frequency and volume, then uses unsupervised clustering to identify profiles that differ markedly from apparently ordinary groups. This requires trader identifiers and enough trade-level data to characterize activity.

A second suggestion compares when trading activity occurs with public news, including changes in volume and orders placed or withdrawn. Granger-causality analysis is offered as a way to examine whether news or trading activity appears to precede the other. The responses are pointers and informal approaches, not a validated detection framework: they provide no feature definitions, thresholds, performance results, or treatment of false positives. Outlier behavior and temporal association can guide review, but neither alone establishes abusive intent or causation.

Key ideas

  • Trader-level attributes can be clustered to find behavioral profiles that stand out from peers.
  • Useful profile features may include trade counts and trading volume.
  • Comparing trading activity with public news can help investigate informational asymmetry.
  • Granger-causality analysis can examine the temporal relationship between news and trading behavior.
  • Clustering outliers and timing patterns are investigative signals, not proof of market abuse.

Tags

EquitiesMachine learningStatisticsMarket microstructureEvent-driven
Full text
# Reference request: Quantitative approaches to market abuse detection


# Reference request: Quantitative approaches to market abuse detection












have been asked to look at some financial timeseries for potential suspicious activity. These are stocks (my background fixed income hybrids trading and not forensic analyst...) and most of the conclusions will be drawn from granular trade level data (spoofing etc).

However, there exist general quantitative / statistical approaches to detection of patterns of activity and informational asymmetry and am wondering if anyone can give me some references (regulatory or otherwise). I found this general survey but would like pointers on journals / books / papers to consult if possible:

www.consob.it/documenti/quaderni/qdf54en.pdf

(also I think Algorithmic Trading by Cartea et al has some paragraphs on infomational asymmetry, which will explore).

There must be a substantial body of research on this, am hoping some might be public domain, can anyone help?

Thanks

EDIT:

There's some interesting pattern recognition work if interested: https://webdocs.cs.ualberta.ca/~zaiane/postscript/DSAA2014.pdf; http://www.ijtef.org/vol7/503-FR00023.pdf

## Answer by mperlow (score 6, accepted)

https://quant.stackexchange.com/a/31951

I can't help as much with public literature, but I did see a talk with a member of the FINRA data science team responsible for exactly this (event link below - perhaps you can track down the speaker).

I don't know the structure of your data, but the approach FINRA took was to develop trader-level attributes (not stock level) to create profiles for each trader (I.e. Number of trades, volume, etc.) and applied unsupervised clustering algorithms to the traders. Once they did so, they determined which neighborhood clusters seemed okay and which were large outliers / potentially malicious. You didn't mention if your data set had trader id's, but this would likely be my approach and FINRA seemed to have success.

I hope this helps and good luck!

http://d1ryye6yw47pmy.cloudfront.net/images/3651/2016_Trading_Event.pdf?1463507984

## Answer by andrew.paul.acosta (score 3)

https://quant.stackexchange.com/a/31992

I cannot speak specifically because I have proprietary insight into the issue, but one approach is to compare the timing of trading activity (volume, bids/offers on the book traded and withdrawn) with publicly-announced news.

Think Granger Causality, and which event seems to cause the other.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.