How are the real-time personalised product recommendations generated?
We are able to bring the most accurate products for every single one of your visitors with the help of clever micro-segmentation through machine-learning technology. Two separate machines are always running, monitoring and learning everything that’s happening on your online store.
The first machine tracks visitor behavior right from the first click. It keeps on learning every action of every visitor like browsing, click, view, add to basket and purchase history. It then uses the behavior data to create micro segments of visitors with similar tendencies.
The second machine collects static data about product aspects like brand, category, price range, color and so on. For each product we identify 3 groups of products that are suitable to be recommended:
1) Alternative Products: Similar products within the same price range. Recommended when the visitor is a price-sensitive customer.
2) Upsell Products: Related products that cost more. Recommended when the visitor is a high-spender.
3) Cross-sell Products : Complementary products, or products that are usually bought together or should be utilized together.
So in the end, when a visitor is looking at a product the first machine identifies the micro-segment the visitor belongs in, all the while the second machine identifies a set of products that should be recommended to them. Each set usually contains 1000 products. Out of that 1000 products, we pinpoint the ones that have been added to basket or purchased by similar customers from the same micro segment as the current one. As a result, we recommend the most accurate and relevant products for every single visitor.
Also, mind we remind you that this is all happening in milliseconds!