Tracking beliefs

You never observe the state of the business. You observe noisy readings of it. Revenue lags settlement, refunds and disputes arrive late, annual plans lump, analytics drops traffic to blockers and bots, and attribution is approximate everywhere.

Two operations, and almost every metric argument needs one of them:

• Filtering - given a series of noisy readings, what is the underlying level, and is the latest move larger than noise explains?
• Updating - given evidence, how should belief shift across competing explanations?

Workflow