Unverified50% confidenceFactExact time
In an A/B test on 50% of traffic, Coinbase's agent reduced fraudulent transactions by 30% and fraudulent amounts by 22%, with the fraud losses saved being about 3 times the inference cost.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedThe model reduced false positive rates by 14% in fraud detection.67% similarUnverified据 ProfitWell 的研究数据，被动流失通常占总流失的 20%-40%，且可以通过支付重试机制（dunning）和过期提醒等技术手段显著降低67% similarUnverifiedIn imbalanced classification problems such as fraud detection, fraudulent transactions typically account for only 0.1%–0.5% of total transaction volume.66% similarUnverifiedAccording to hands-on testing by Bilibili UP host "1024工程笔记," integrating Ponytail reduced code volume by 54%, lowered token consumption by approximately 20%, and kept security-related check items at 100% passing.66% similarUnverifiedIn the control test, relying solely on prompts to instruct the AI to write less code saved about 30% of lines, but security dropped to 95%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1027822API
curl https://kongchang.com/api/v1/knowledge/claims/1027822MCP
get_claim(id=1027822)