How Wickes used machine learning to fuel hyper-personalised targeting

Machine learning helped the home improvement retailer develop personalised communications for its two target audiences – everyday consumers and the professional market.

In 2021, Wickes had a challenge to overcome. The retailer had two distinct customer bases – everyday consumers and tradespeople.

While consumers associated Wickes with specific products rather than their whole project, professionals tended to shop from six categories or less, supplementing with rival brands. To increase market share, the retailer needed consumers to think and buy differently.

Enter the Mission Motivation Engine, developed in collaboration with Team ITG and Emerald Thinking. The machine learning model incorporates online and in-store transactional, search, browsing, engagement and third-party data, with insight into how consumers click on social, display and website content.

Behaviour was broken into missions and motivations, alongside an analysis of the aptitude motivation for each segment – namely the level of ability and willingness to take on a project.

The Mission Motivation Engine identified 10 DIY/showroom missions, seven trade professional missions, seven motivational trade segments, 11 TradePro programmes and 10 DIY/showroom programmes.

Wickes used this data to target shoppers. The retailer combined email, app, social and landing page channels to guide consumers through their DIY project. A bold creative concept swapped talk of sales with friendly hints and tips.

The insight revealed tradespeople preferred to shop on Sunday night and Monday morning to get organised for the week. The team developed personalised weekly communications under ‘The Week Ahead’ banner, adopting a new tone of voice and personalised ‘to-do’ list, positioning Wickes as the trade’s default supplier.

Not only did this approach help Wickes win the Marketing Week Award for Best Use of Segmentation, the model delivered £7m in incremental revenue within six months.

Recommended

Comments

    Leave a comment