Households about to leave
Five signals that a household is about to cancel (a bad box in flight, a cart they rejected, the promo cliff, a skip streak, an unanswered ticket), each with a policy that acts under a ceiling and the exceptions that go to a person.
A sample of the app on simulated data. Book a call to click through it live, or to see it on your own exports.
One working session with the people in the seat: which decisions, which systems, what a good week looks like.
The app you see above, running on your own exports instead of the simulated world. Every screen, every decision, your numbers.
Wired to your systems with your permissions, agents proposing, people approving, the ledger recording who did what.
Overview
A credit that arrives before the box does keeps more households than silence, at a known cost. The app measures that on the last seven weeks and sets the other four rules against it. Boxes in flight move on the map; households with a signal sit where they live.
Decisions it produces
- Let the policies handle everyone inside their ceilings
- Credit, re-personalize, offer, or call a household
- Add ice or switch carrier on a lane
The world it runs on
A simulated subscription grocer: about 700,000 households, five fulfillment centers, a thousand SKUs, a recommendation engine that fills most of the box. 25,000 sampled households over eight weeks with the causal links written down: demand from recommendations, shortages from lead time, bad boxes from lanes and weather, tickets from bad boxes.
Every company, person and number in this demo is simulated; anchors are public facts or plausible for the segment. Substitute your own feeds and the same apps run on your operation, with your permissions.