Method
Fraud scoring
Risk scoring and classification of fraudulent or abusive behavior.
13 cases from 10 companies apply Fraud scoring. 8 report results in production.
Typical tasks: Catch fraud and abuse, Moderate content at scale, Detect anomalies, Optimize decisions and 2 more. Companies: Yandex, Stripe, BlaBlaCar, Ramp, LinkedIn, Uber and 4 more. Often combined with: Rule-based heuristics, Gradient boosting, Graph features, Human / expert labeling, SHAP and 21 more.
| Putting a Transformer Inside Every Card Authorization | fintech | 2026-10 | |
About Anti-Fraud and Cats: How to Fight Fraud, Not Just Detect It Better![]() | ![]() | general | 2026-05 |
| ML Scoring of 3DS Authentications in a Payment SystemNS | NS | fintech | 2026-05 |
| The ML flywheel: How we continually improve our models to reduce card testing | fintech | 2024-12 | |
Graphs in Anti-Fraud and How We Apply Them![]() | ![]() | social | 2024-11 |
| How LinkedIn Audience Network protects advertisers from invalid traffic | adtech | 2024-08 | |
| Leverage graph technology for real-time Fraud Detection and Prevention | travel | 2024-07 | |
| Stopping Uber Fraudsters Through Risk Challenges | mobility | 2024-01 | |
How we used machine learning to fight fraud at BlaBlaCar — Part 1![]() | ![]() | mobility | 2023-06 |
How we built our Machine Learning Pipeline to fight fraud at BlaBlaCar — Part 2![]() | ![]() | mobility | 2023-06 |
| How we built it: Stripe Radar | fintech | 2023-03 | |
| Graph for fraud detection | mobility | 2022-11 | |
| Automation of Strategy Generation for Anomaly Detection in E-Commerce | e-commerce | 2022-07 |

