Observed arrival · 2026-09-04
ChannelMoa, the Korean YouTube outlier detector
A Korean YouTube research tool that ranks videos by how far they have exceeded their channel’s usual performance, rather than by raw views.
Field notes
The scoring baseline is each channel’s recent one-year median, not raw subscriber count or total views, which lets smaller channels surface alongside established ones. The visible dataset lists 8,181 tracked channels and 381,508 analyzed videos, with examples including 2,199.5x and 1,728.6x breakouts. ChannelMoa also describes similar-channel search, cross-market gap research, and alerts for monitored channels, though the extract does not verify which of those require login.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue