Journal of Operational Risk

Risk.net

Predictive fraud analytics: B-tests

Sergey Afanasiev and Anastasiya Smirnova

This paper considers:

  • B-tests – predictors for bank internal fraud detection, as a generalization of the Benford's law;
  • Metrics of proximity of two distributions, for the calibration of B-tests;
  • Target variable of potential loss, allowing to adjust operational B-tests;
  • Results of B-tests' calibration on a sample of bank loan applications.

In the banking sector, machine-learning methods are applied in a wide variety of business areas: assessing a client’s risk profile (application and behavior scoring), forming targeted sales (x-sell, up-sell), choosing collection strategies (collection scoring), etc. The bank anti-fraud division is no exception, where with the help of machine-learning methods effective anti-fraud tools are developed. This paper deals with B-tests: methods by which it is possible to identify internal fraud among employees and partners of the bank at an early stage.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to Risk.net? View our subscription options

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here