ao link
Twitter
Facebook
Linked In
RSS
Login or Register
New to InternetRetailing?
Register Now
Internet Retailing

This is your 1 complimentary article for this month

Become a member for unlimited and immediate access.


Register
Already a member? Log in here

How AI has lifted IKEA’s AOV by 2% worldwide

Linked InTwitterFacebookeCard
IKEA: AI creates new ways to sell
IKEA: AI creates new ways to sell
Sharelines

IKEA has upped AOV by 2% using AI-powered recommendations – here the head of engineering explains how they did it

Artificial Intelligence-powered product recommendations and a more scientific approach to data has seen IKEA lift average order value (AOV) by 2% worldwide. Here Albert Bertlisson, head of engineering at Edge at IKEA Retail (Ingka Group) explains how the company did it.

 

“At IKEA we have multiple places in our customer journey in various channels where different kinds of personalisation can deliver a superior customer experience,” he says. “Product recommendations in the shopping basket, content recommendations in editorial sections, inspirational recommendations on product pages and more.

 

“After a while in the broader ‘recommendations’ team there was a decision to split the team to have one sub-team focused on product recommendations. The pandemic altered customer behaviour and needs as well. At that inflection point we decided to change our way of working and dive head-first into a more scientific approach to handle the operational complexities of delivering high quality product recommendations at scale. We deemed this necessary to improve our level of personalization and to have a holistic understanding of our customers.”

 

Data driven decisions

Bertlisson says: “The first step was to radically improve our ability to get high-quality quantitative information to understand how our ‘recommendation’ solutions affected personalization. We did this through high volume A/B testing on customer behaviour and after initial experimentation, we had a few key learnings: first, the mix of both UX and algorithms are really important for a cohesive customer experience; and second, the quality of personalisation can’t be measured in silos. Statistical significance can be attained by testing several groups of recommendations at once.”

 

He continues: “Once we came up with a solid framework for gathering data and acknowledged how little we knew about our customers, we were able to explore an incredible number of creative options - nothing was off the table. This was a very humbling experience, in that it opened up new perspectives for personalization, a more curious and less confined way of thinking. We learned to trust the data because it might show you things you don’t expect.”

 

Experimentation and learning framework

According to Bertlisson, IKEA’s teams then created ways to quickly deploy experimental modifications to its existing solution. This enabled experimentation in the front-end with the user experience, including details in headings and images. This also covered tweaks in the backend with anything from detailed manual additions or removals of recommendations to mixing and matching of various algorithms both home grown and from Recommendations AI.

 

He says: “This flexibility came with an overhead--more complexity and cost relative to directly retrieving recommendations from Recommendations AI. However, the benefit was that we were no longer dependent on manual evaluation of what made for a good recommendation system. We aligned on a data-driven and qualitative approach to provisioning recommendations and significantly accelerated our experimentation timeline. Together with optimization of the CI/CD pipeline this enabled the team to take an idea or hypothesis from inception to A/B testing with customers in less than half an hour.”

 

Recommendations AI experiments

The team’s infrastructure was already running on GCP and when it received early access to Recommendations AI, the requirements to get started were minimal and that allowed it to start with initial tests requiring minimal effort and investment, Bertlisson explains.

 

“We started with a few use-cases and identified places where our existing recommendation algorithms needed improvement or complementary recommendations. We also explored additional ways where more useful information could be presented to the customers through personalized recommendations.”

 

Recommendations AI model combinations

While Recommendations AI might be considered a simple API to get a set of product recommendations, as the team dived deeper into the solution it became apparent that it could be tweaked in several different ways to offer many fine tuning configurations to meet business goals.

 

While too much fine tuning and customisation could lead to sub-par performance, in general Bertlisson found that it was a great strategy to give several versions of ML-powered recommendations to work with. “The further you personalise the experience, the more options you have to likely pick the best one for the customer,” he says

.

Recommendations AI models such as ‘Recommended for you’, ‘Frequently Bought Together’ and ‘Others you may like’; are coupled with business goals including optimising for conversion rate, click through rate and revenue.

 

“We experimented with many different model combinations and custom rules,” Bertlisson adds. “All this was easily configurable right in the GCP console. One of the simplest custom configurations we used was to only recommend items that were in stock, and when items were out of stock we looked at similar items that were available to augment the experience.”

 

Collaboration with Google

“Our collaboration with Google Cloud accelerated our learning process during experimentation,” says Bertlisson. “We worked closely together early in the product development. Additionally, their model provided flexibility to change direction and allow for more options than we had previously. Ultimately, this provided us a way to drastically improve our time to market with a product that produced tremendous results that we could not have accomplished on our own.”

 

Results and takeaways

With more personalised and real-time recommendations available IKEA was able to increase the number of relevant recommendations displayed on a page by +400%. To accommodate the wider repertoire of recommendations it had to change the user experience. For example, in some places we had horizontally scrolling displays of product recommendations which were much easier for customers to use.

 

Another consequence of displaying more personalised recommendations was tangible improvement to conversion rate and average order value. Recommendations AI algorithms helped customers in two ways: firstly, customers were able to find products that they liked quickly and establish their preferred choice among other options more quickly as well, giving them confidence to make a purchase through much fewer clicks. Even though we previously already had well-tuned recommendations of several types, with Recommendations AI we measured +30% improvement in click through rates.

 

Secondly, average order value saw a +2% surge with numerous examples of how Recommendations AI could help customers find both attractive and directly complementary products, expanding the customer purchase from a single product to an entire home furnishing solution.

 

 

“As a direct effect of having stronger business results, the team started exploring more places in the customer journey where our growing buffet of recommendations could be used,” says Bertlisson. “We’d start with an initial experiment to answer if displaying recommendations in the specific context made sense at all. Frequently the data that emerged from these experiments prodded us to iterate further on what additional types of recommendations would be most appropriate to show to the customer as the customer’s behaviour evolved. Today, most of IKEA’s site recommendations are powered by Recommendations AI.”

 

One key takeaway is that for some types of personalised recommendations there are benefits to using advanced algorithms that require a lot of high level data science and engineering competence to build since they outperform simplistic approaches. In some places, simplistic approaches work very well and in others the right decision is to not have product recommendations at all. For an effective use of product recommendations you need to have all the above options and the ability to tell when to use which one.

 

Next steps

When working with something so tightly related to customer experience, there is a constant change in user behaviour and new learnings to observe and adapt to, observers Bertlisson. Product recommendations are rarely the main standalone experience and frequently something that is used to help and enhance an experience.

 

“We see a lot of value in having a large toolbox of possible options and a team with a relentless focus on collaboration to improve the customer experience,” he says. “We’re working directly with the Recommendations AI team and experimenting with several new features that we’re excited about.”

 

In the future IKEA see opportunities of improving the customer journey through a more visual experience that inspires the customer rather than relying on customers to use their imagination to visualise groups of products together. Vision Product Search provides that and is something Bertlisson says IKEA is looking into deploying next.

Linked InTwitterFacebookeCard

The InternetRetailing Newsletter

A curated update containing news analysis, reports, podcasts and opinion - completely free and delivered three times weekly

Become a Member

Create your own public-facing profile
Gain access to all Top500 research
Personalise your experience on IR.net
Internet Retailing
We are the magazine, portal and research source for European ecommerce and multichannel retail, hosting the board-level conversation for retailers, pureplays and brands across all of our platforms. Join the conversation.

© InternetRetailing Media

Latest Tweet

Internet Retailing
Tamebay
eDelivery
Twitter
Facebook
Linked In
Youtube
RSS
RSS
Youtube
Google
Linked In
Facebook
Twitter