Enhanced Recommendation Models for Ecommerce

Upgrade your recommendation engine with better data for greater per-session value and revenues
The ecommerce industry is increasingly known for its fast-paced and competitive nature. Sellers have a few seconds at most to capture their users’ attention, so highlighting the right blend of products immediately is critical to converting visitors to customers. Building tools that can help create relevant and useful recommendations is essential, but it requires the right data to work smoothly.
The problem

An up-and-coming ecommerce brand has been working on improving their website user experience by showing relevant products immediately when visitors land on their homepage. The problem is that the company’s recommendations are based exclusively on their internal data, limiting their effectiveness when dealing with new users, and offering limited results to existing ones.

The solution

Our customer built two parallel models to improve their recommendation engine — one for existing users, and one for cold-start recommendations. The models were built on smarter user profiles based on enriched datasets. 

The existing user recommendation model uses historic purchase data, as well as users’ clicks, pages visited, and other website data, and connects it with data from Explorium, including: 

  • Social media activity and presence 
  • Employment and demographic information
  • Internet behavior on other websites

The cold-start user recommendation builds profiles for new users with no prior history on the site. It connects with Explorium’s Enrichment Catalog to take advantage of the following data: 

  • Search engine queries for similar products
  • Demographic data connected to purchasing habits and user IP  
  • Preferences and habits based on installed apps 
  • Economic information including estimated income and economic stability
The results:

Increased per-session value and revenue

The result has been a 17% increase in per-session value for each visitor to the site and improving overall revenues for the company’s website by 4% on a monthly basis. More importantly, the company has been able to make its website more dynamic depending on the visitor, whether new or returning.

Upgrade your recommendation models with external data for greater per-session value and revenues.

Other resources you might be interested in

Just announced! Explorium Announces $31M in Series B Funding to Accelerate Growth Read more