Ecommerce ops · Production

END. Clothing adopts Algolia to enhance search and recommendations on its global retail website

The problem

END. Clothing's existing search solution lacked advanced features and offered no pathway to AI-based solutions, creating gaps in its ability to deliver a seamless, community-oriented customer journey across multiple locales.

Workflow diagram · grounded in source
1
Customer searches or browses site
trigger
“END. deployed Algolia across its site wherever it requires search and indexing functionality”
2
Algolia Search processes query
ai_action
“The company implemented Algolia for Search, Browse and are working to surface Recommend into its Adobe Commerce-based site”
3
Dynamic Re-ranking reorders results
ai_action
“Algolia's Dynamic Re-ranking (DRR) capabilities against manual merchandising. She found DRR performed "really, really well," which has reduced the workload for her team”
4
Customer data fed to Recommend
integration
“sending the right amount of information to Algolia —customer information, transaction information, price, stock level, etc. — to feed this into Recommendations”
5
Recommend generates product suggestions
ai_action
“so that we can get good product recommendations out without teams needing to manually curate' which is what they previously did!”
6
Alternatives shown for dead-end journeys
output
“Instead of turning to a competitor for an out-of-stock product, customers are now given alternatives that meet their criteria”
7
A/B testing validates DRR performance
validation
“A/B testing with DRR led a 1.47% increase in site conversion rate”
Reported outcome

Algolia's Dynamic Re-ranking lifted site conversion rate by 1.47% in A/B testing and overall conversions by 2%, while reducing the merchandising team's workload and improving click-through rates on product listing pages.

Reported metrics
site conversion rate (A/B test DRR)1.47%
Conversions2%
Merchandising workloadReduced merchandising workload
click-through rates on PLPsImproved click-through rates on PLPs
Show all 5 reported metrics
site conversion rate (A/B test DRR)1.47%
conversions2%
merchandising workloadReduced merchandising workload
click-through rates on PLPsImproved click-through rates on PLPs
revenue from Dynamic Re-rankingSignificant revenue uplift
Reported stack
AlgoliaRecommendDynamic Re-rankingRulesPersonalizationA/B TestingAdobe Commerce (Magento)
Source
https://www.algolia.com/customers/END.
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Algolia's Dynamic Re-ranking lifted site conversion rate by 1.47% in A/B testing and overall conversions by 2%, while reducing the merchandising team's workload and improving click-through rates on product listing pages.

What tools did this team use?

Algolia, Recommend, Dynamic Re-ranking, Rules, Personalization, A/B Testing, Adobe Commerce (Magento).

What results were reported?

site conversion rate (A/B test DRR): 1.47%; Conversions: 2%; Merchandising workload: Reduced merchandising workload; click-through rates on PLPs: Improved click-through rates on PLPs (source-reported, not independently verified).

How is this ecommerce ops AI workflow structured?

Customer searches or browses site → Algolia Search processes query → Dynamic Re-ranking reorders results → Customer data fed to Recommend → Recommend generates product suggestions → Alternatives shown for dead-end journeys → A/B testing validates DRR performance.

Related ecommerce ops cases