Securing Merchants: Combatting Scams and Fraud for Trust
summary
Company Moonay runs an internal ML model plus multiple third‑party fraud vendors and manual reviews, uses wallet screening vendors to flag known scam addresses, and requires customers to accept terms twice; 2021 chargebacks total around $14M and law‑enforcement cites ~$575M in investment fraud. Monthly trainings, a dedicated chargeback team, transaction holds for live outreach, and targeted KYC/liveness checks together reduce friendly fraud and block scams in experiments, though banks and chargeback rules still leave merchants financially exposed.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:12About Moonay and crypto infrastructure
- 3:17Scams social engineering friendly fraud
- 8:54Common scam types
- 13:47Preventing and mitigating scams
- 21:08Challenges and collaboration
- 25:44Industry collaboration and reporting
- 27:06Q&A compliance staffing
- 28:55Q&A crypto vs banking scams
- 31:19Q&A money laundering fraud models
related talks
13mHarnessing Machine Learning to Combat E-commerce Fraud
26mAI-Powered Fraud Detection in Cloud-Native Digital Payments
32mHow Top Operators Fight Fraud in Crypto & Gaming
24mTop Fraud Trends in Crypto for 2024 and How to Stay Ahead in 2025
45mAnti-Fraud in Reverse and the Use of ML Methods in It
47mTrain, Evaluate, Repeat: Building a Credit Card Fraud Detection System
39mA New Era of Fraud: What Role Can Cyber Play?
48mScaling a cryptocurrency exchange using Data Science & Machine learning