Lacuna/Labs
deep-finance-causal-forest-ads
deep purple
#594 / 601

NAME

deep-finance-causal-forest-ads — "Promoted Listings worked on your wedding pieces (+18% conversion) but had no effect on gift items. Scope the ads to wedding listings only."

SYNOPSIS

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

DESCRIPTION

Instead of asking 'do ads work on average,' ask 'do ads work on THIS subgroup.' A forest of decision trees finds the buyer segments where the ad pays off and the segments where it's wasted.

"Promoted Listings worked on your wedding pieces (+18% conversion) but had no effect on gift items. Scope the ads to wedding listings only."

MECHANISM

DATAyour cortexFITCausal ForestPOSTERIORcredible bandFORECASTdecision

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

EXAMPLES

Sakura uses this when you suspect your ad spend works in some places but not others. A causal forest splits buyers and listings into subgroups and asks "where did this ad actually change behavior?" — "Promoted Listings lifted wedding pieces 18%. Gift items: no effect. Scope the ads."

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.

SEE ALSO

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)