Skip to main content

​
Overview

Soft boost is a sorting technique that lifts products matching specific conditions toward a target score. Unlike priority rules that cluster boosted products at the top, soft boost creates natural interleaving by lifting matched products only as much as needed to reach a target band. Soft boosts appear in the sort order editor with a Modifier badge and are visually grouped beneath the metric or attribute they modify. This tree layout makes it easy to see which expression each soft boost targets.

​
How soft boost works

Soft boost supports two modes: Amplify strong performers (multiplicative, the default) and Lift matches into view (additive). Each mode uses a different formula to lift products matching specific conditions.
  • Amplify strong performers (multiplicative) — pushes matching products that already rank well on the underlying metric even higher. Use when matches have real metric data.
  • Lift matches into view (additive) — surfaces matching products regardless of their metric value. Use for new arrivals or restocks with little data.
Both modes also enforce a minimum spacing between boosted matches so a cluster of matches never lands adjacent in the final results — see Min positions between. If you want matches to stay clustered in score order instead, turn off Keep matches spaced out.

​
Amplify strong performers (multiplicative, default)

This mode applies a decaying multiplier to the base score. This produces natural interleaving because:
  • Products with low base scores get a larger relative boost (the exponential decay is minimal).
  • Products with high base scores get a smaller relative boost (the exponential decay is significant).
  • Non-matching products receive no boost (multiplier = 1).
The score stays the primary signal — a weakly matched product will not leapfrog a stronger non-match. When two or more matches would otherwise land adjacent at the top, Min positions between spreads them out; a single match keeps its natural position. Limitation: Amplify strong performers does not move products whose base value is zero. New arrivals with no sales remain stuck at the bottom regardless of boost settings. Use Lift matches into view for those cases.

​
Lift matches into view (additive)

This mode lifts matching products in value space to a target score derived from the rest of the catalog. The target is the value at the chosen percentile of the base metric across all candidate products. Each matched product is lifted the full distance to that target, so the whole cohort lands on the same score regardless of its own base value. A product whose base score is already above the target stays where it is. Lift matches into view never demotes a matching product. Because every match lands on the same value, use Min positions between to control how the cohort is spaced through results. Percentile Target decides where the matched cohort lands; Min positions between decides how far apart consecutive matches sit around that landing point. Key advantages:
  • Works with zero base values: Products with no sales data can still be lifted effectively.
  • Value-space targeting: Control how high boosted products land relative to the rest of the catalog, expressed as a percentile of the base metric.
  • Predictable landing: Every match lands on the percentile target, so the cohort’s position depends only on Percentile Target, not on each product’s own base value.
  • Ideal for new arrivals: Sprinkle new products with no performance history into established rankings.
  • Combines cleanly: Multiple Lift matches into view boosts on the same metric add their lifts together for predictable layering.
When to use Lift matches into view:
  • Boosting products with zero or near-zero base values (new arrivals, products with no sales).
  • Targeting a specific spot in the value distribution (for example, lifting matches to roughly the top quartile of sales).
  • Sprinkling new products into a best-selling sort order without clustering them at the top.
Lift matches into view (additive) was updated on 2026-08-20 so that Percentile Target alone decides where matches land. Any Boost Strength stored on an additive boost is ignored, so a strength value the editor could not reach no longer caps the lift below the target. If an existing additive boost was placing matches lower than Percentile Target implies, reopen the sort order and preview it — you may want to lower the percentile to keep the previous placement.
Min positions between became authoritative on 2026-07-01. The slider (previously labeled Decay Rate) now controls the minimum spacing between consecutive boosted matches in both boost modes. Sort orders created before that date may still carry legacy slider values (for example, 100 or 500) that predate the 1–50 range — reopen each soft-boost expression, preview the result, and reset Min positions between to a value in the current range if the spacing looks off.

​
Soft boost vs. priority rules

Example: For a collection sorted by sales with a soft boost on tags = 'featured':
  • Priority Rule: All featured products appear first, regardless of sales
  • Soft Boost: Featured products with low sales get a significant boost, but high-selling non-featured products can still rank higher

​
Configuration parameters

​
Boost mode

Determines the formula used to boost matching products.
  • Options: Amplify strong performers (multiplicative, default) or Lift matches into view (additive)
  • Default: Amplify strong performers
Amplify strong performers (multiplicative):
  • Pushes matching products that already rank well on the underlying metric even higher.
  • Multiplies the base value by a decaying boost factor.
  • Best for products with non-zero base values — use when matches have real metric data.
  • Uses Boost Strength, Keep matches spaced out, and Min positions between.
Lift matches into view (additive):
  • Surfaces matching products regardless of their metric value.
  • Lifts every matching product to the same percentile-based target on the same metric.
  • Works even when the base value is 0.
  • Uses Percentile Target, Keep matches spaced out, and Min positions between. Boost Strength does not apply in this mode.
  • Ideal for new arrivals or restocks with no performance data.

​
Boost strength

Amplitude of the multiplier applied to the base score in Amplify strong performers mode. Higher values produce a stronger lift, especially for low-base-value products.
  • Range: 0 to 10
  • Default: 0.25
  • Recommended: 0.25 to 1.0 for subtle promotion, 1.0 to 2.0 for stronger effects.
  • Only used in Amplify strong performers mode. In Lift matches into view mode, Percentile Target alone controls where matches land, so Boost Strength is ignored even if it was stored on the boost.

​
Percentile target (Lift matches into view only)

The target value for matched products in Lift matches into view mode, expressed as a percentile of the base metric across the candidate set. A higher percentile lifts matched products further up the ranking.
  • Range: 0 to 100
  • Default: 50
  • Recommended: 50–75 for moderate visibility, 75–90 for high visibility.
  • Only used in Lift matches into view mode.
Example impact when sorting by sales (descending):
  • Percentile Target 50: Matches land on the median sales value, blending into the middle of results.
  • Percentile Target 75: Matches land on the value at the 75th percentile, roughly in the top quartile.
  • Percentile Target 90: Matches land on the value at the 90th percentile, near the top.
  • Percentile Target 100: Matches land on the top base value, above every non-matched product.
A product whose base score is already above the percentile target stays where it is. Lift matches into view never demotes a matching product.

​
Keep matches spaced out

Controls whether Layers enforces spacing between boosted matches. When on (the default), matches are spread apart using Min positions between. When off, matches are allowed to sit next to each other in pure score order.
  • Options: On (default) or Off
  • Default: On
Turn this off when you want boosted matches to clump together — for example, when a promotion should present as a solid block at the top of results rather than being interleaved with non-matches. How it applies in each mode:
  • Amplify strong performers: Matches are ordered by their boosted score, highest first, with no forced gaps between them.
  • Lift matches into view: Matches land contiguously at the percentile anchor instead of being spread out with a stride, so the cohort sits together in score order.
When Keep matches spaced out is off, the Min positions between control is hidden because it no longer applies.

​
Min positions between

Controls the minimum number of non-matched products that sit between two consecutive boosted matches in the final results. This prevents clustered matches from landing adjacent to one another, even when their scores would otherwise push them together at the top.
  • Range: 1 to 50
  • Default: 10
  • Recommended: 5–15 for a light rhythm, 20+ for aggressive spacing.
How it applies in each mode:
  • Amplify strong performers: A single match stays at its natural score position. When two or more matches would cluster, they are spread apart with at least this many non-matches between them, starting from the top-ranked match. Score order among matches is preserved.
  • Lift matches into view: Percentile Target determines where the matched cohort is anchored. Min positions between then lays matches out from that anchor with the chosen stride, interleaving non-matched products in the gaps.
Overflow: When there are more matches than the spacing budget can fit, the extra matches fall back to their natural (non-boosted) position and lose the boosted badge, so the spaced set stays gapped and never collapses at the tail.

​
Configuration requirements

Soft boost requires a metric or product attribute to modify. If no sortable expression exists in the sort order, an error dialog appears explaining that you need to add at least one metric or attribute first.
When you add a soft boost, it is automatically inserted above the last metric or attribute in the list so that it modifies that expression. You can reorder expressions after insertion if needed.

​
Supported base attributes

Soft boost works over any sortable metric or numeric product attribute, including:
  • Numeric metafields stored as text (for example, a custom.rating metafield whose value is "4.7"). Non-numeric or empty values are treated as 0 for boost math instead of failing the query.
  • Date attributes such as created_at, updated_at, or published_at. When you configure a multiplicative boost over a date attribute, Layers automatically applies it as an additive percentile lift instead — the multiplicative formula is not meaningful over raw date values, and the additive shape produces the intended lift over any monotonic numeric base. If the date attribute has a Bucket set (Hour, Day, Week, Month, Quarter, or Year), the soft boost uses the same bucketed value as its base, so matches on products from the same period get the same lift instead of splitting on raw timestamp.

​
Example use cases

Boost products tagged as “featured” while maintaining sales-based ranking:
Result: Featured products with moderate sales rank higher, but top-selling non-featured products can still win.

​
Boost multiple tags (Amplify strong performers)

When using in or notIn operators, you can boost products matching any of multiple values. The UI enables multi-select when these operators are selected.
Result: Products with any of the specified tags receive a boost, creating natural interleaving based on their sales performance.

​
Exclude price ranges (Amplify strong performers)

Use the not between operator to demote products in specific price ranges:
Result: Products priced between 100−100-200 receive a negative boost, pushing them lower in results while maintaining natural ranking.

​
Boost products with specific attributes set

Use is not null to boost products that have specific attributes configured:
Result: Products with a featured end date configured receive a boost, useful for time-sensitive promotions.

​
Sprinkle new arrivals into best sellers (Lift matches into view)

Interleave new arrivals with zero sales into a best-selling sort order:
Why Lift matches into view? New arrivals have zero sales, so Amplify strong performers would not move them. Lift matches into view lifts matching products to the value at the 75th percentile of sales, so products with no sales history land in the upper portion of results. Result: New arrivals with zero sales land on the value at the 75th percentile of sales, spaced through the results by Min positions between. As new products accumulate sales, their base score rises above the target and they take their organic position. Use case: Perfect for fashion retailers launching seasonal collections, where new items need visibility before they have sales history. A Percentile Target of 75 places new arrivals prominently without completely dominating the sort order.

​
Layer multiple lift boosts (Lift matches into view)

Stack two or more Lift matches into view boosts on the same metric to combine effects predictably. When a product matches more than one boost, the lifts add together, so it lands higher than a product matching just one:
Result: Products tagged with campaign-spring land on the 80th-percentile value, new arrivals land on the 60th-percentile value, and products tagged with both receive the combined lift and land above either single-match cohort. Non-matching best sellers remain competitive based on their organic sales.

​
Highlight recently published products (Amplify strong performers)

Give recently published products a boost without completely overriding popularity:
Result: New products get visibility while established bestsellers remain competitive.

​
Regional preference (Amplify strong performers)

Boost products from specific vendors for certain markets:
Result: Local brand products rank higher while maintaining relevance-based ordering.

​
Works with other features

Soft boost integrates with other sort order capabilities:
  • Segmented Metrics: Apply soft boost to segmented metric scores for personalized boosting
  • Sequences: Soft boost respects product sequences when enabled
  • Multiple attributes: Chain multiple soft boosts or combine with weighted sorting
  • User Affinity: User Affinity reuses the same boost-mode model, applying the lift to products that match an individual shopper’s learned tastes on browse pages

​
Best practices

  • Choose the right mode: Use Amplify strong performers for products with non-zero base values, and Lift matches into view for products with zero or near-zero values (like new arrivals).
  • Start with sensible defaults: Begin with Boost Strength 0.25 in Amplify strong performers, or Percentile Target 75 in Lift matches into view. Adjust based on what you see in preview.
  • Preview before publishing: Use the sort order preview to verify that the right products are being boosted and that the lift looks reasonable. Each matched product shows a +N% badge with its computed lift.
  • Avoid over-boosting: In Amplify strong performers, keep Boost Strength below 1.0 for most use cases to maintain natural ranking. In Lift matches into view, lower Percentile Target if matches are landing too high.
  • Layer lift boosts intentionally: When stacking multiple Lift matches into view boosts on the same metric, lifts add together, so a product matching several boosts lands above one matching just one. Use lower per-boost Percentile Target values when several boosts can match the same product.
  • Use Lift matches into view for zero values: When boosting products with no performance data, always use Lift matches into view. Amplify strong performers cannot move products with a base score of zero.
  • Retune existing additive boosts: Sort orders using Lift matches into view created before 2026-08-20 may carry a stored Boost Strength that is now ignored. If matches are landing higher than before, lower Percentile Target to restore the previous placement.

​
See also