A Supervised Auto-Tuning Approach for a Banking Fraud Detection System

@inproceedings{Carminati2017ASA,
  title={A Supervised Auto-Tuning Approach for a Banking Fraud Detection System},
  author={Michele Carminati and Luca Valentini and Stefano Zanero},
  booktitle={CSCML},
  year={2017}
}
In this paper, we propose an extension to Banksealer, one of the most recent and effective banking fraud detection systems. In particular, until now Banksealer was unable to exploit analyst feedback to self-tune and improve its performance. It also depended on a complex set of parameters that had to be tuned by hand before operations. 

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We show that the proposed system was able to detect sophisticated frauds, improving Banksealer’s performance of up to 35% in some cases.
  • We show that the proposed system was able to detect sophisticated frauds improving Banksealer’s performance up to a factor of 35%.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Choosing Snps Using Feature Selection

  • J. Bioinformatics and Computational Biology
  • 2006
VIEW 1 EXCERPT