Recommendation Campaigns

Recommendation campaigns rank catalog products for a site and placement. Their quality depends on catalog health, stable interaction events, and a configuration that has an explicit fallback.

Before you create a campaign

• The site is active and the browser SDK is installed.
• Active catalog products have stable IDs, titles, prices, currency, availability, and safe destination URLs.
• Product view, cart, purchase, recommendation impression, and recommendation click events use the same product IDs.
• Embeddings are ready for content-based or hybrid behavior. Product updates normally queue refresh work automatically.

Choose an algorithm

Dashboard option	Use when	Controls
Store rules	You need deterministic merchandising logic.	A Primary rule (same category or brand, price range, frequently bought together, recently viewed, or popular) and Rule priority (0–1).
Product similarity	Product attributes, product fields, and embeddings are strong.	Similarity threshold and category weight.
Shopper behavior	Interaction volume is sufficient.	Minimum confidence and a popular-products fallback.
Balanced	You want behavior with a content fallback.	Behavior and similarity weights, plus a popular, recent, or random fallback.

Shopper behavior needs enough interaction history before it outperforms simpler options. Start with Balanced or Store rules on new or low-traffic sites.

Configure placement

1. Choose the site and campaign name.
2. Select carousel, grid, or list.
3. Choose product page, cart, checkout, home, category, search results, or custom placement.
4. For a custom placement, provide a stable CSS selector owned by the storefront theme.
5. Set minimum and maximum product counts. The renderer should not display an underfilled result below your minimum.

Configure targeting

Recommendation campaigns can target saved Audiences (activation-ready audiences), Shopper segments, page patterns, and device types, and can exclude purchased or out-of-stock products.

Campaigns can additionally use consented Profile boosts and Intent boosts. Recently purchased IDs are excluded unless Replenishment mode allows them. The Reach preview for intent targeting is an inventory estimate, not a guarantee that every request changes.

Test and activate

1. Save as Draft.
2. Request recommendations from a matching page and site.
3. Verify safe product URLs, currency, availability, count, and fallback behavior.
4. Check identified and anonymous visitors separately.
5. Activate only after impression and click tracking are present.

For controlled comparisons, select Create experiment to compare 2–5 recommendation configurations with exactly one control. See Experiments for planning, lifecycle, and results.

Measure

The SDK and custom surfaces use:

• recommendation_impression with recommendation_id and campaign_id;
• recommendation_click with those IDs plus product_id;
• signed product touchpoints that can later be matched to an authoritative commerce conversion as assistance.

Analytics labels these outcomes as Upsurge assisted. An assisted conversion gives the recommendation zero referral credit and does not replace or modify AWIN, CJ, or another acquisition source. Assisted value is kept by currency and is non-additive because more than one Upsurge product may assist the same order.

Troubleshooting

• No products: check site scope, active status, catalog status, placement context, minimum count, and campaign status.
• Irrelevant results: confirm product IDs and categories, embeddings, algorithm weights, and fallback strategy.
• Wrong visitor context: verify identify(), device ID behavior, consent, and activation fields allowed for recommendations.
• Quiz result failure: a quiz request with require_campaign=true fails for a missing, cross-site, paused, or archived recommendation campaign instead of silently falling back.