Fighting Financial Fraud with Targeted Friction

David from the Trust team walks us through how Airbnb battles chargebacks while minimizing impact to good guests.

The piano in our “Vienna” meeting room in San Francisco has an easter egg. Move the right book, and it will play for you!

What We’re Fighting: Chargebacks

Optimizing the Model Threshold

Cost of a False Positive

Cost of a False Negative

Cost of a True Positive

Figure 1: Schematic diagram of Good user dropout and Fraudster dropout experiments.

Example: Comparing Blocking a Transaction versus Applying a Friction

Figure 2: Example ROC curve of a ML model predicting P(fraud)
Figure 3(a): Blocking events, a friction with F=1 and G=1. Figure 3(b): Applying a friction with F=0.95 and G=0.1

Final Thoughts



Creative engineers and data scientists building a world where you can belong anywhere.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store