Personalized Recommendations at Dixons Carphone

Dixons Carphone leverages behavioral data with award-winning use of AI to improve customer experience


  • Bundle attach rates on their website was lower than in-store
  • Initial product attachment effort was a manual process (no personalization)
  • Dixons built a generic collaborative filtering recommendation model but were unable to productionize it on their website
  • Adobe analytics data was very complex and difficult to view at an individual level


Syntasa plugged natively into Dixons Carphone’s existing technologies and within their GCP environment to synthesize behavioral data so that it could be available for analysis right away. To produce personalized recommendations, Syntasa built a Nearest Neighbor model to generate a neighborhood of similar customers, based on browsing behavior and products purchased together by similar customers.

Use Cases

  • AI-Assisted Merchandising
  • Product Recommendations
  • Identity Resolution
  • Adobe Analytics Adapter


  • Product coverage has doubled
  • Add-to-basket rates have increased 3x

Bundle Coverage and Add-to-basket Rates

Slider image

“Syntasa has been really invaluable in speeding up our time to value by architecting our Adobe Analytics data and productionizing data science and machine learning modeling at scale, and in such a way that we can confidently pass that into production systems to drive the user experience.”

Slider image

“What we had a challenge with was the ability to look at the granular detail of the user-level data, so that we can start to look at what an individual customer is doing (and might do) on our website.”

See Syntasa in action

Actions speak louder than words. See what an AI assisted customer intelligence platform looks like in action.