Meet JD Sports

U.K.-based JD Sports has a long-standing reputation for dressing and lacing up athletes and sneaker enthusiasts across the Atlantic and beyond.

Founded in 1981 in the Greater Manchester market town of Bury, JD Sports has grown into a global sports fashion retailer, with Finish Line, founded in Indianapolis in 1976, forming an important part of its U.S. business. Together, the brands have built their success by supplying just the right sneaker or piece of athletic apparel to savvy customers who expect seamless shopping. Online, that demands search functionality that’s ultra-relevant, frictionless and adapts to fast-changing trends, seasonality and real-time customer behavior.

“Finding the right sneaker or apparel item needs to feel effortless, whether browsing a broad category page or searching for a specific drop,” says Kristin Matter VP, Digital Operations at JD Sports.

The Challenge: From Manual Merchandising to MACH-Ready Search

Burdened with a highly manual search tool, as the brands’ product catalogs grew, managing that search experience and its product listing pages (PLPs) became increasingly resource-intensive for the merchandising teams.

“Merchandising teams spent a significant amount of time manually tuning results, boosting products and creating static rules that struggled to keep pace with fast-changing customer trends and seasonality,” Kristin explains.

In addition, the company’s technology team began the process of modernizing its ecommerce systems through a MACH architecture built around agility, modularity, and speed. This transformation forced the technology team to rethink how core systems, like search and discovery, fit into its new API-driven, composable architecture.

“We wanted to move away from monolithic e-commerce platforms and build a flexible tech stack capable of powering seamless omnichannel experiences across digital and physical channels,” Kristin says.

The teams needed an intelligent, modern search platform that could automate merchandising logic, deliver ultra-relevant vector search at scale and seamlessly integrate into the new architecture it was building.

The Solution: Building a Scalable AI Search Foundation with Algolia Professional Services

The company turned to Algolia in 2024 to meet the strict demands of its new search platform. The solution stood out from competitors, Kristin says, because of its powerful blend of speed, AI-driven automation and robust API capabilities.

“Algolia was a natural fit for our vision,” she says. “Its API-first design allowed us to plug high-performance search and discovery capabilities directly into our headless frontends with minimal friction.” 

She adds that during implementation, Algolia’s Professional Services team worked closely with JD Sports’ digital team to deeply understand its business strategy, ranking requirements and merchandising needs. Together, they translated those requirements into the best technical approach, from ensuring the right data was sent to Algolia to designing a data model that could support the customer experience JD Sports envisioned. Just as importantly, the foundation gave merchandising teams the flexibility to create and manage rules effectively without relying on additional development work.

The team focused first on a smooth migration: deploying core search functionality, PLP rendering and basic analytics across all storefronts. From that solid foundation, it shifted rapidly into optimization and feature expansion, moving from basic keyword matching to more advanced AI-driven capabilities such as NeuralSearch, Data Transformations and Collections.

The team also rolled out Dynamic Re-Ranking (DRR) on category pages in 2025, shifting from reactive manual merchandising to algorithmic search results based on real-time customer behavior. “Before Algolia, adapting results to real-time micro-trends required manual intervention that often lagged behind actual shopper behavior,” Kristin explains. “Today, DRR autonomously identifies what’s trending based on real click and conversion signals, automatically promoting hot products to top positions on category pages.”

She adds that following implementation, Algolia’s Customer Success team continued to work proactively with the JD Sports tech team on ongoing optimization, regularly providing performance data for review, helping test new features and identifying opportunities to drive even more value from the platform.

The Results: Stepping Up Efficiency, Engagement and Revenue

That close collaboration equipped JD Sports with a scalable, API-based search foundation that dramatically reduces manual merchandising effort and gives customers a more intuitive, fluid browsing experience. 

“The biggest impact has been operational efficiency,” Kristin notes. “Previously, merchandisers spent countless hours tweaking ranking rules and manually building static collection pages.” 

“Today, we’ve drastically streamlined PLP management. By letting Algolia’s algorithms optimize item ordering dynamically based on real-time popularity and conversions, our merchandising team spends far less time on manual intervention and more time on strategic planning.”

She adds that millions of athletes, enthusiasts and sneaker-lovers across JD Sports’ digital channels, including Finish Line, now experience a smoother, faster and more intuitive product discovery experience, whether searching for a specific brand or browsing a high-level category page, leading to higher engagement and faster discovery.

“Thanks to Algolia, shoppers now see trend-aware, highly relevant results immediately, whether searching for a specific brand or browsing a high-level category page, leading to higher engagement and faster discovery,” Kristin says.

The business impact is clear:

• 16% jump in PLP revenue

• 22% increase in revenue from search

• Search click-through rates (CTR) climb 7.65%

• PLP click-through rates (CTR) rise by 73%

“Dynamic Re-ranking alone delivered an immediate increase of 2.2% CTR, 4% add-to-cart rate and 4% conversion rate,” Kristin says. “With it, we can now deliver personalized, high-converting browsing experiences globally without scaling manual effort.”

Looking forward, she says the digital team is eager to take advantage of Algolia’s AI strength to make the shift to smart merchandising: moving from manual analysis to automated intelligence that can analyze macro data trends and surface proactive insights, alerting merchandisers to new opportunities like rising search trends, inventory shifts or underperforming categories.

And it’s not the only AI-fueled use of Algolia the team is exploring. Algolia is already plugged directly into the ecommerce platform’s customer-facing AI shopping agent, Kristin says, acting as a high-speed product and search engine that supplies hyper-relevant, real-time results to answer customer queries and drive conversions.

It’s all to enhance the customer experience, driving conversions through hyper-personalization at scale. In the months and years to come, she continues, “We aim to further tailor every touchpoint so that search results, PLP orderings and product recommendations dynamically reflect individual shopper preferences, past purchases and real-time intent across all digital channels.”