National RetailerE-commerce & Personalization

28% higher conversion with AI-driven personalization

A major Dutch retailer increased online conversion by 28% through personalized product recommendations and dynamic content.

28% higher conversion
with AI-driven personalization
  • 28%Higher conversion
  • 45%More repeat purchases
  • 3.2xROI on implementation
  • 2.1MCustomer profiles
Sector
E-commerce
1Background

The challenge

With over 2 million customers and 50,000 products, it was impossible to manually make relevant recommendations. The generic 'bestseller' approach resulted in low conversion and high bounce rates.

Key problems

  • 01Generic product recommendations for all visitors
  • 02Low click-through rates on email campaigns
  • 03High cart abandonment due to irrelevant upsells
  • 04No real-time personalization possible
Magazijnmedewerkers tussen de orderstellingen
2Methodologie

Our approach

We built a system that makes recommendations during the visit, based on customer behavior, product characteristics, and the situation of that moment.

  1. 01

    One view per customer

    Website behavior, purchase history, and email interactions come together in one profile per customer.

  2. 02

    Recommendations tailored to the customer

    We developed models that look at what similar customers buy and at the characteristics of the product, for different contact moments.

  3. 03

    The right recommendation straight away

    Recommendations are calculated within a fraction of a second, so on the website and in emails they match what the customer is doing right then.

  4. 04

    Testing continuously

    Two variants are tested side by side, so the recommendations keep getting better.

3ImpactE-commerce

Results

The personalization engine was rolled out across all digital channels and delivered significant improvements within 3 months.

  • 28%Higher conversionThrough relevant product recommendations at key moments
  • 45%More repeat purchasesCustomers return more often due to better experience
  • 62%Higher email CTRPersonalized product blocks in newsletters
  • -35%Lower bounce rateVisitors find what they're looking for faster
“The impact was immediately visible in our KPIs. Within a month we saw significant improvements in conversion and customer engagement.”
Director E-commerceNational Retailer

Technologies

Tools & platforms used

  • Python
  • Apache Spark
  • Redis
  • Google Cloud
  • BigQuery
  • Looker

Interested in this case?

Leave your email and we'll reach out to discuss how we can achieve similar results for your business.

Rutger Geerlings, solution architect at Stratalytic

Rutger Geerlings

Solution architect

What is it about?

No sales pitch, no newsletter. We only use your details for this conversation.

Thirty minutes to see where the biggest impact is.

An honest estimate in numbers, even if the answer is that it does not pay off.