Dixon's carphone warehouse improves user experience and increases sales with a chatbot

Machine Learning - Dixons


The purchase cycle begins before we even enter the store.

Companies in the retail sector know that most of the time the purchase cycle begins even before the customer enters the store with his credit card ready to pay for the product. Customers search the internet before they purchase to read reviews, compare products and even prices.


Customers are actively searching for information.

The Electronics retailer, Dixon's Carphone Warehouse in the UK is no exception to the rule. In a recent study they found out that 90% of their customers started the shopping journey online and that 65% used their mobile phones to assist them while they were on the store. In order to boost customer engagement and assist their potential clients on all phases of their purchase cycle,  they developed a digital assistant (chatbot), powered by state of the art Artificial Intelligence, that is able to understand the customer's questions and provide relevant answers. 


Meet Cami the chatbot.


The digital assistant was named Cami and it is available both in the Currys brand website and on Facebook Messenger​ and it helps both employees and customers research, find, save products and check stock. Cami also recognises pictures in order to recognise products.



I keep hearing about chatbots all the time, what's new here?


This article was written inspired by the original story published here.
Chatbots have been a hot trend lately, especially in the marketing world. But since they were traditionally built around a predefined and static discussion tree of answers, most of the time the experience tended to be unsatisfying.


For a chatbot to work properly, the technology behind it needs to:


  • Correctly understand the context and the question itself.
  • Provide a relevant answer.


This used to be impossible to implement just a couple of years ago. 


Artificial Intelligence to the rescue!


The obvious and only answer for building this type of solution is to leverage on some type of Artificial Intelligence. Thankfully, cloud giant and Technology leader Microsoft has amazing developer products ready for this!


This specific project was developed using the Microsoft Bot Framework, which provides developers with a rich bot building environment, but it also leverages on Language Understanding Intelligent Service (LUIS) for conversational abilities, as well as on Computer Vision to process images. Both these apis are part of the Microsoft Cognitive Services cloud offering and are incredibly inexpensive to use, or even free below a certain threshold.


MLab, the Machine Learning specialists at your service!


If Machine Learning inspires you and you think you would like to implement a use case in your organisation, please contact us. We are vendor agnostic and we will recommend and integrate the technology that adapts the best to your needs. If available technologies don't satisfy your needs, we can always train a custom model tailored to your project.


DisclaimerMLab was not involved in the development of this project. We simply publish this case study as a source of inspiration on what Machine Learning can achieve.