Ecommerce ops · Production

Leroy Merlin Brasil achieves 31% CTR increase and $28M annual revenue boost with Algolia AI Search

The problem

Leroy Merlin Brasil's existing Elasticsearch search engine was too inflexible to scale, requiring significant developer involvement for even simple changes, while poor speed and irrelevant results degraded the customer experience across its large, diverse product catalog spanning multiple complex categories.

First attempt

The previous Elasticsearch search engine required developers to constantly debug and manually analyze search result rankings, and even simple changes demanded full team involvement and significant coding.

Workflow diagram · grounded in source
1
Customer initiates product search
trigger
“Today, Algolia powers search and navigation across desktop, mobile and in-app customer experiences, supporting the company's omnichannel presence”
2
Dynamic Re-ranking reorders results
ai_action
“Dynamic Re-ranking for more relevant results and to drive KPIs”
3
Data Transformations build custom ranking
ai_action
“Data Transformations — which it is used to create custom ranking attributes based on multiple weights and signals”
4
A/B Testing validates optimization
validation
“Gabriel and Pereira's team uses A/B Testing regularly to optimize search for customers, refine rankings across platforms and improve its impact on the business”
5
Business teams continuously refine
feedback_loop
“the ability for business and merchandising teams to refine and optimize search independently ensures that results stay continuously aligned with Leroy Merlin's commercial strategy and omnichannel vision”
Reported outcome

Leroy Merlin Brasil achieved a 31% increase in click-through rate, a 15% increase in add-to-cart from search, and an estimated annual revenue increase of more than $28 million, while business teams can now independently manage and optimize search without large dedicated technical staff.

Reported metrics
Click-through rate (percentage points)+3.8% p.p.
Add-to-cart from search (percentage points)+1.7% p.p.
Estimated annual revenue boost (key results box)$28 million annually
Click-through rate (relative)+31%
Show all 8 reported metrics
click-through rate (percentage points)+3.8% p.p.
add-to-cart from search (percentage points)+1.7% p.p.
estimated annual revenue boost (key results box)$28 million annually
click-through rate (relative)+31%
add-to-cart from search (relative)+15%
estimated annual revenue increase (results section)more than $28 million
operational cost reductionsignificantly reduces operational costs
initial migration timelineabout three months
Reported stack
AlgoliaElasticsearchQuery SuggestionsDynamic Re-rankingNeuralSearchData Transformations
Source
https://www.algolia.com/customers/leroy-merlin-brasil
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Leroy Merlin Brasil achieved a 31% increase in click-through rate, a 15% increase in add-to-cart from search, and an estimated annual revenue increase of more than $28 million, while business teams can now independent…

What tools did this team use?

Algolia, Elasticsearch, Query Suggestions, Dynamic Re-ranking, NeuralSearch, Data Transformations.

What results were reported?

Click-through rate (percentage points): +3.8% p.p.; Add-to-cart from search (percentage points): +1.7% p.p.; Estimated annual revenue boost (key results box): $28 million annually; Click-through rate (relative): +31% (source-reported, not independently verified).

What failed first in this deployment?

The previous Elasticsearch search engine required developers to constantly debug and manually analyze search result rankings, and even simple changes demanded full team involvement and significant coding.

How is this ecommerce ops AI workflow structured?

Customer initiates product search → Dynamic Re-ranking reorders results → Data Transformations build custom ranking → A/B Testing validates optimization → Business teams continuously refine.

Related ecommerce ops cases