Solving the False Positives Problem in Fraud Prediction Using Automated Feature Engineering.

Wedge, R., Kanter, J. M., Veeramachaneni, K., Rubio, S. M., & Perez, S. I. (2018). Solving the False Positives Problem in Fraud Prediction Using Automated Feature Engineering. Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2018).

Type

Book chapter

Intellectual base

Review or monograph

Year

2018

DOI

10.1007/978-3-030-10997-4_23

ISBN

9783030109967

Link

https://doi.org/10.1007/978-3-030-10997-4_23

Cited from

systems_cybernetics

Cited by

1 citation across 1 artifact.

Each citation links to the sentence it supports in the citing article.

Primes

• Self Engagement Under Misclassification
  • Add classifier inputs for better discrimination — multi-spectral IFF, multi-receptor immune recognition, multi-feature fraud models.

    This sourceShows that adding classifier inputs (237 automatically engineered behavioral features) cut fraud false positives by ~54% while preserving detection — the classifier-side fix (more inputs, tuned to cost asymmetry) that reduces self-harm without weakening defense.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:5ffd08aa8820 · see in the full table