Products, articles or pages that are browsed together by visitors are tracked by the system and based on a visitor’s preferences relevant recommendations are shown. If the algorithm fails to find similar items in the same category, it searches for categories that are viewed together the most, revealing the most searched product of that category.
Visitors are recommended products that are usually bought together to increase the AOV of each purchase. If the algorithm fails to find products that are purchased together in the same category, the algorithm brings the most purchased product of the most related category.
When a campaign threshold exists as a prerequisite to receive an incentive,
the algorithm recommends complementary products which will help the visitor reach the required order value.
A visitor’s browsing behaviour is compared to other visitors’ journeys and historical data to create a list of relevant recommendations increasing the probability of more items being discovered.