Ecommerce ops · Production

Gymshark adds Algolia Recommend to boost Black Friday order rates by 150%

The problem

Gymshark's previous recommendation solution required extensive manual configuration and constant upkeep, creating operational burden and limiting the team's ability to improve recommendation quality efficiently.

First attempt

The prior recommendation solution demanded so much manual configuration and constant upkeep when making changes that the team spent significant effort on maintenance rather than improving recommendation quality.

Workflow diagram · grounded in source
1
Customer visits product page
trigger
“Through A/B testing on related products on product detail pages (PDPs)”
2
AI recommendation generation
ai_action
“Algolia Recommend is a simple, flexible API used to build AI-powered recommendations using as little as six lines of code”
3
Recommendations displayed to user
output
“Users seeing Algolia recommendations were clicking on more products: 1.4 clicks per user compared to 1.1 with the previous solution”
4
A/B test validates performance
validation
“During a two-week period, Gymshark tested Algolia against its previous solution to get a complete picture of how it could improve performance”
5
Iterative improvement and expansion
feedback_loop
“Gymshark expects even better as they unlock more of the full potential of Algolia Recommend, such as the customization of recommendations”
Reported outcome

Algolia Recommend delivered a 150% increase in order rate and 32% increase in add-to-cart rate with new users on Black Friday, a 13% higher order rate for returning customers, and reduced manual configuration burden on the IT team.

Reported metrics
order rate increase (new users, Black Friday)150%
add to cart rate (new users, Black Friday)32%
Order rate higher (returning customers)13% higher
Add to cart rate higher (returning customers)10% higher
Show all 9 reported metrics
order rate increase (new users, Black Friday)150%
add to cart rate (new users, Black Friday)32%
order rate higher (returning customers)13% higher
add to cart rate higher (returning customers)10% higher
clicks per user vs previous solution1.4 clicks per user vs. 1.1
order rate from clicked recommendations (Netherlands A/B test)5.5%
mobile order rate (all markets test)150 percent
mobile recommendations use growth (Black Friday)16%
IT staff demand for maintenanceReduced demand on IT staff around configuration and maintenance
Reported stack
AlgoliaAlgolia RecommendShopifyContentfulReactAWS
Source
https://www.algolia.com/customers/gymshark-recommend
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Algolia Recommend delivered a 150% increase in order rate and 32% increase in add-to-cart rate with new users on Black Friday, a 13% higher order rate for returning customers, and reduced manual configuration burden o…

What tools did this team use?

Algolia, Algolia Recommend, Shopify, Contentful, React, AWS.

What results were reported?

order rate increase (new users, Black Friday): 150%; add to cart rate (new users, Black Friday): 32%; Order rate higher (returning customers): 13% higher; Add to cart rate higher (returning customers): 10% higher (source-reported, not independently verified).

What failed first in this deployment?

The prior recommendation solution demanded so much manual configuration and constant upkeep when making changes that the team spent significant effort on maintenance rather than improving recommendation quality.

How is this ecommerce ops AI workflow structured?

Customer visits product page → AI recommendation generation → Recommendations displayed to user → A/B test validates performance → Iterative improvement and expansion.