Ecommerce ops · Production

Clarks adopts Algolia Search and Recommend to support its MACH journey

The problem

Clarks' existing SAP Hybris e-commerce platform was reaching end of life and its on-premises hosting was becoming unsustainable. The monolithic architecture made it extremely difficult to make changes, be flexible, or scale.

Workflow diagram · grounded in source
1
Customer initiates search
trigger
“customers have been able to find products much more easily”
2
Autocomplete assists query
ai_action
“the company is taking advantage of the solution's autocomplete functionality. This has made searching for the company's footwear more intuitive and efficient, greatly improving the customer experience.”
3
ML recommendations surface products
ai_action
“It has the capability to learn from what people are browsing and make sure that it surfaces to the next customer with similar browsing behaviors. And because it's constantly learning, it continuously becomes more expert in its recommenda…”
4
Dynamic Re-ranking orders results
ai_action
“While the Clarks team used to spend hours on merchandising pages, they can now let DDR do the work for them.”
5
Merchandiser adjusts product priority
human_review
“We have the ability to chop and change around product ordering, so we can promote the products we want to sell first, or those that make the best margin, or which we have the biggest stock of — we can position those and entice the custom…”
6
Omni-channel process integration
integration
“Processes like refunds and restocking have become seamlessly integrated between channels, enhancing customer experience but also reducing operational costs and delays.”
Reported outcome

Clarks improved customer search and browsing experience with AI-driven recommendations and autocomplete, reduced time spent on merchandising through Dynamic Re-ranking, and achieved fewer product returns, lower operational costs, and increased profits.

Reported metrics
Customer search and browsing experienceimproved dramatically
Time on merchandising pagesused to spend hours; now let DDR do the work
Product returnsfewer returns
Operational costs and delaysreducing operational costs and delays
Reported stack
Algolia SearchDynamic Re-RankingRecommendSAP HybrisCommercetoolsAmplienceAkeneoGridDynamics
Source
https://www.algolia.com/customers/Clarks
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Clarks improved customer search and browsing experience with AI-driven recommendations and autocomplete, reduced time spent on merchandising through Dynamic Re-ranking, and achieved fewer product returns, lower operat…

What tools did this team use?

Algolia Search, Dynamic Re-Ranking, Recommend, SAP Hybris, Commercetools, Amplience, Akeneo, GridDynamics.

What results were reported?

Customer search and browsing experience: improved dramatically; Time on merchandising pages: used to spend hours; now let DDR do the work; Product returns: fewer returns; Operational costs and delays: reducing operational costs and delays (source-reported, not independently verified).

How is this ecommerce ops AI workflow structured?

Customer initiates search → Autocomplete assists query → ML recommendations surface products → Dynamic Re-ranking orders results → Merchandiser adjusts product priority → Omni-channel process integration.

Related ecommerce ops cases