The Challenge

Treating all its customers as an extension of the MDV family, the retailer wanted to move away from a one-size-fits-all approach to its newsletters, making them more relevant to each recipient’s tastes and interests.

MDV’s marketing team wanted to personalise the contents of each newsletter depending on factors such as category and style affinity, and whether the recipient is interested in mens- or womenswear.

But determining customer tastes and interests relies on making sense of the complex interactions between multiple data points, and with a small marketing team, the prospect of manually carrying out the extensive customer segmentation needed to personalise its newsletters prevented the retailer from moving forward with its strategy.

So MDV called upon Ometria’s Predictive Segmentation functionality to build customer audiences that the marketing team could use to personalise its newsletters.

The Solution

Using Ometria’s predictive segmentation engine, a series of mutually exclusive customer segments were created combining gender and category preference (for example, ‘womenswear preference and shorts’) for MDV’s regular ‘new in’ email.

Instead of using manual segmentation, the audience for each of these segments was automatically created, using machine learning to determine each individual’s affinity towards certain categories.

The algorithm takes into account factors such as:

• The individual’s purchase and browsing behaviour.
• Relationships between similar people and products.
• Temporal correlations, based on the buying cycle of each product.
• Reinforcement learning, based on whether a shopper responds to machine-generated predictions in the expected way.

Emails with personalised content and subject lines, tailored to the category affinity of the recipient, were sent to each segment.