deep-finance-bsts-causal(automation) · Curator Automations

NAME

deep-finance-bsts-causal — "Stopping Google Shopping for two weeks: posterior says you'd have lost $1,200 (99% probability the effect was positive)."

SYNOPSIS

id deep-finance-bsts-causal tier deep-purple section §22. Finance — AI/subsystem + deep-purple cluster (37) trigger operator-asked shape PLAYBOOK

DESCRIPTION

Did the ad cause the spike, or would the spike have happened anyway? We build a parallel-universe model of what sales would have looked like WITHOUT the ad, then measure the gap. Same math NASA uses to know whether a policy actually moved a metric.

"Stopping Google Shopping for two weeks: posterior says you'd have lost $1,200 (99% probability the effect was positive)."

MECHANISM

not-yet-implemented — no cart file at curator-web/src/scheme/carts/…/deep-finance-bsts-causal.sks

EXAMPLES

Sakura uses this when you ask "did stopping Google Shopping cost me money?" She builds a synthetic control of what your revenue would have been with the ads still running, compares it to what actually happened, and reports the gap with a probability attached. "99% probability you lost about $1,200."

TIER

deep purple

deep reasoning · batched · dollars per run

FITNESS

Not yet

This method only gives a real answer above a sample threshold. Running it on a small shop produces a confidence band the size of the universe — useless. When the shop crosses the threshold, this lights up.

HISTORY

canonical source: curator/docs/AUTOMATIONS-CANONICAL.md · §22-finance-aisubsystem-deep-purple-cluster-37
last regenerated: 2026-06-05 20:31 UTC (mechanical — edits land in the MD or sidecars, not here)

KNOWN BUGS

(none recorded — flag in AUTOMATIONS-CANONICAL.md or open an issue against the cart file)