Dixons Carphone, one of the largest consumer electronics retailers in Europe, was recognized with the “Best Use of AI” award at the 2019 eCommerce Awards in London. The eCommerce Awards showcase the best online retailers, online companies, agencies, innovators, products, and campaigns in the ecommerce industry. Dixons Carphone, which uses Syntasa to deliver real-time personalized recommendations to customers, won the award for their innovative use of AI to improve customer experience.
How Dixons Carphone implemented AI
Dixons Carphone, whose primary brands include Currys PC World and Carphone Warehouse, turned to Syntasa to help them provide their customers with personalised product suggestion journeys on their websites. Dixons recognized that one of the most valuable aspects of the traditional retail shopping experience is personalised recommendations from sales professionals, and wanted to find a way to replicate that experience online.
Dixons engaged Syntasa to implement a real-time recommender system to drive incremental sales and increase margins for their business. Syntasa plugged natively into Dixons existing technologies and within their GCP environment to synthesize behavioral data in real-time so that it would be available for analysis and action. Thea data science team within the Dixons e-commerce department built an algorithm they call Natural Attach using shopping cart data that produces non-personalized recommendations. To produce personalized recommendations, Syntasa built a model called Nearest Neighbor to generate a neighborhood of similar customers, based on browsing behavior and products purchased together by similar customers. Both models were then productionized with Syntasa’s platform.
Now, when a customer arrives at the Currys PC World websites and views a product detail page, a query is made to the recommendation API, containing the customer’s visitor ID and product ID. This recommendation API then returns personalized bundle recommendations, based on the customer’s history on the Currys PC World websites (if the customer hasn’t spent any time on the site, they receive non-personalized recommendations based on aggregate data of other users).
Producing meaningful results
Dixons’ implementation of AI-driven personalized recommendations produced powerful results. Add-to-basket rates increased 3x for customers provided with personalized recommendations while shopping online — clearly suggesting that these recommendations resonated with consumers and reflected their needs. Even for those customers who were new to the site and hadn’t generated enough data yet for personalized recommendations, Dixons’ non-personalized data-driven recommendations outperformed the previous manually-created ones by 1.3x.
With Syntasa’s help, Dixons can now seamlessly combine multiple enterprise and behavioral data sources into their big data environment, build machine learning models, and activate that data on channels including their website, optimization tools, and CRM.
Says Paula Bobbett, Head of Online Performance at Dixons Carphone, “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.”
Everyone at the Syntasa team congratulates Dixons on their recent eCommerce Award and is excited to hear about their continued success!
