BIG W improves search conversion by 7% and basket size by 4.7% with Algolia AI Search
After re-platforming to headless commerce, BIG W found its existing search engine was compromising the customer experience with highly irrelevant results, while a small web development team meant any replacement had to be robust and require minimal ongoing technical investment.
BIG W's previous search engine, Solr on a Hybris backend, delivered highly irrelevant results — a query for 'blue socks' would surface unrelated blue items and generic socks, with the correct match buried on page four or five.
After deploying Algolia Search and Recommend, BIG W reduced search exits by 10%, improved conversion from search by 7%, increased basket size by 4.7%, and improved NPS by 4 points.
Frequently asked questions
What did this team achieve with this AI workflow?
After deploying Algolia Search and Recommend, BIG W reduced search exits by 10%, improved conversion from search by 7%, increased basket size by 4.7%, and improved NPS by 4 points.
What tools did this team use?
Algolia Search, Algolia Recommend, Dynamic Re-Ranking, Query Suggestions, Rules, Merchandising Studio, Adobe Experience Manager (AEM), Shopify Plus.
What results were reported?
Search exits: 10%; Basket size: 4.7%; Conversion from search: 7%; NPS: +4pts (source-reported, not independently verified).
What failed first in this deployment?
BIG W's previous search engine, Solr on a Hybris backend, delivered highly irrelevant results — a query for 'blue socks' would surface unrelated blue items and generic socks, with the correct match buried on page four…
How is this ecommerce ops AI workflow structured?
Customer searches product catalogue → AI re-ranking applied to results → Recommendation carousels displayed → Real-time analytics feed re-ranking.