Constructor Blog | Ecommerce Search Industry and Product Information

Data Science Paper Review – Overview of RecSys

Written by Constructor Team | Jun 29, 2020 7:00:00 AM

It’s a fundamental question for any eCommerce business looking to implement advanced search and discovery features:

What’s the process for building a recommendation system? How can you compute similarities between objects to serve products that users are likely to purchase?

In this video, Constructor’s data science team will walk you through some of the most influential papers on building recommendation systems, the pros and cons of the methods discussed in each paper, and much more — from the basic co-occurrence methods used in 1994 to Graph Convolutional Neural Networks used today like PinSage.

Take a look:

 

 

Want to learn more about optimizing on-site search to drive real business metrics?

For years, retailers have optimized search solely on “relevance,” hoping the results that users want to see (and the results that drive important business metrics) appear at the top.

This is exactly wrong — and it’s not how companies like Google and Amazon optimize their search.

Watch our webinar discussing the limitations of optimizing search results for “relevance,” and the 3 attributes retailers should focus on to drive real business results from search. Check it out here: