Overview
Ranking relevancy gives you direct control over how products are ordered in text search results. Every search result is scored using a combination of signals — semantic similarity, keyword matching, engagement metrics, freshness, and inventory status. You can adjust how much each signal contributes to the final score, and create rules that boost, bury, or pin specific products for particular queries.
The ranking relevancy system has two main areas:
- Signal weights control the global balance between the five signal groups that make up every search score.
- Ranking rules apply conditional adjustments — promoting, demoting, or pinning products when specific search queries are detected.
Signal groups
Every text search score is composed of five signal groups. Each group contributes a percentage of the total score, and all group weights always sum to 100%.
| Signal group | What it measures | Sub-signals |
|---|
| Semantic | How closely product content matches the meaning of the query | Text similarity, image similarity |
| Keyword | How well exact terms in the query match product fields | Per-field matching across title, description, vendor, and other searchable attributes |
| Engagement | How customers interact with products | Click-through rate, purchase rate, add-to-cart rate, revenue |
| Freshness | How recently the product was published | Publication date recency |
| Inventory | Whether the product is in stock | Stock availability |
Sub-signals
Within each group, individual sub-signals can also be tuned:
- Semantic — Adjust the balance between text similarity and image similarity. If your catalog relies heavily on visual discovery, increasing image similarity weight helps surface visually relevant products.
- Engagement — Adjust the relative importance of click-through rate, purchase rate, add-to-cart rate, and revenue. For example, weighting purchase rate higher than click-through rate rewards products that convert, not just products that attract clicks.
- Keyword — Sub-signal weights for keyword matching are derived from your attribute configuration and are displayed as read-only values.
How normalization works
When you adjust one signal group’s weight, the remaining groups are automatically rebalanced so that all weights continue to sum to 100%. This means you can increase the importance of one signal without manually reducing every other signal.
Avoid setting any single signal group above 70%. Over-concentrating weight on one group can reduce result diversity and make rankings less responsive to other quality signals.
Ranking rules
Ranking rules let you create conditional adjustments that modify search rankings when specific conditions are met. Each rule has a name, a scope, optional targeting conditions, and one or more actions.
Rule types
Manual rules define attribute-based conditions to boost or bury products. For example, you can boost all products from a specific vendor or bury products tagged as “clearance” for particular search queries.
Visual rules let you pin products to exact positions in search results using a drag-and-drop interface. Search for a query, then drag products into the order you want them to appear.
Scope
Each rule has a scope that determines when it fires:
- Global — Applies to every text search, regardless of what the customer searches for.
- Query-specific — Applies only when the search query matches a targeting condition.
Targeting conditions
Query-specific rules support three matching modes:
| Mode | Behavior | Example |
|---|
| Exact match | Query must equal the value exactly (case-insensitive) | “summer dress” matches only “summer dress” |
| Contains | Query must contain the value as a substring | ”dress” matches “red summer dress collection” |
| Semantic match | Query must be semantically similar above a configurable threshold | ”summer dress” could match “sundress” or “beach outfit” |
Actions
| Action | Effect | Configuration |
|---|
| Boost | Promotes products matching an attribute filter higher in results | Attribute + operator + value + strength (1–50%) |
| Bury | Demotes products matching an attribute filter lower in results | Attribute + operator + value + strength (1–50%) |
| Pin | Locks specific products to exact positions in results | Product selection + position (max 50 pinned products) |
How rules are evaluated
Ranking rules only apply to text searches. When a text search is executed:
- All enabled rules for your store are loaded.
- Global rules are applied to every search.
- Query-specific rules are checked against the search query using their targeting condition.
- Matching rules apply their actions — boost and bury actions adjust product scores, while pin actions lock products to fixed positions.
If multiple rules match the same search, all of their actions are applied. Boost and bury adjustments are additive, with a maximum combined magnitude of 50%.
Search preview
The signal weights page includes a live search preview that shows how products would rank with your current weight configuration. You can:
- Type a search query and see ranked results instantly.
- Toggle ranking rules on or off to compare their impact.
- View a per-product score breakdown showing how each signal group contributed to the product’s ranking.
- See which ranking rules were applied to each product (shown as “Boosted”, “Buried”, or “Pinned” badges).
The preview reflects unsaved weight changes, so you can experiment before committing.
See also
