Choose a recommendation use case

Choose what needs a recommendation and what may be recommended. DinMo calls these the source and candidate scopes.

Match the output to the business need

Business need	Source → candidates	Result
Personalized products or offers	Users → items	Up to K ranked items per user.
Related products	Items → items	Up to K related items per source item, excluding the item itself.
An audience for each offer	Items → users	Up to K ranked users per item. The same user may appear in several audiences.
Brand or category preferences	Users → vendor or category values	Up to K ranked values per user. Requires the corresponding item attribute mapping.
An audience for each brand or category	Vendor or category values → users	Up to K ranked users per value. Audiences may overlap.
One campaign audience distributed between offers	Users → items, with audience allocation	At most one assignment per selected user, plus a separate top-K ranking.

In configuration, these correspond to user-to-item, item-to-item, item-to-user, and user-to-attribute directions. A vendor or category grain changes the entity being recommended; it does not return a specific product.

For example, to rank tomorrow's sales for each customer, use the sale or deal IDs as items. Ranking vendors answers a different question when a vendor has several sales.

Define both scopes

A source scope determines who or what receives a recommendation. A candidate scope determines what can appear in the result. Restricting one does not restrict the other.

For personalized offers, a typical setup is:

• Sources: customers who can be contacted for this campaign.

• Candidates: items matching the campaign's stock, visibility, status, and activity rules.

Use segments to express those rules. They are resolved for the run; recheck eligibility before activation if the data has changed.

For vendor or category scenarios, the selected items define the available attribute values. Use the product grain when item-level eligibility and item-level output are essential.

Item availability

An explicit item segment can include offers that have not opened yet, allowing you to prepare tomorrow's campaign today without changing the decision date.

• For products recommended to users and related products, this applies to the candidate item segment.

• For users recommended to an item, this applies to the source item segment.

• A user segment alone does not enable future items.

Future items explicitly selected this way are not excluded merely because they open after the scenario's objective horizon. Items with a known end date at or before the decision time remain excluded. Without an explicit item segment, future-opening items remain excluded.

The source item of a related-products scenario can be historical or ended: it is the reference item, not the offer being delivered. Historical evaluation retains its own chronological availability rules.

Preparing a recommendation is not permission to activate an offer early. Schedule delivery using the catalog's opening dates and recheck current availability.

For non-overlapping campaign audiences, continue with Build and allocate audiences.