Two business requests often arrive under the same name.
| Request | Example | Learning problem | Evidence you need |
|---|---|---|---|
| Recommend a relevant product or plan | Which of 50,000 products should appear on the homepage? | Candidate retrieval and ranking | Customer–item interactions, item metadata, exposure and position logs |
| Recommend an incentive or next action | Should this customer receive free shipping, a coupon, a reminder, or nothing? | Treatment-effect estimation and constrained policy choice | Eligible decision opportunities, assigned actions, a control group, action probabilities, outcomes and costs |
A product can be relevant without needing a discount. A customer may be likely to redeem a coupon and just as likely to buy at full price. A model trained to predict redemption often favours such customers, because redemption is easier to predict than behaviour changed by the offer. Attribution reports and conversion probabilities cannot show incrementality, the sales the offer caused. Microsoft's incrementality documentation draws the same line between attributed conversions and causal impact.
For this guide, picture a retailer or subscription service with a small, explicit action set:
no_offer, reminder, free_shipping, and coupon_10. A reminder is an active treatment if it
sends a message. The no-offer control gets your defined usual experience. Note whether that includes
other campaigns. For retention, connect this policy to the churn guide. For an offer
that changes the selling price, use the demand and margin method in the
pricing guide.
Write the contract before you choose a model:
- Decision: one action for an eligible customer or account, at a stated time, through a stated channel. If the decision is a whole ranked slate, say so, because its logging and evaluation differ.
- Outcome: contribution profit over, for example, the next 30 days, with time for returns to arrive. Count every transaction, whatever the coupon redemption or click attribution.
- Comparison: a no-offer policy and the current business policy. A new policy must beat both, on the same eligible population and accounting rules.
- Constraints: consent, eligibility, stock, minimum margin, contact limits, total spend, concurrent campaigns, and any limits the business sets.
- Guardrails: complaints, unsubscribes, returns, service load, and longer-term buying or renewal behaviour. Set the thresholds that matter before you see the result.