How to drive retail sales and improve customer experience with recommendation systems

In part one of a three part series, we'll go over the data science behind attribute similarities for your customer recommendation system.


July 13, 2022

11:00 am PDT




Wesley (Wes) Cobb, Senior Data Scientist

Wesley Cobb

Senior Data Scientist

Cori Hendon - Data Science Solution Architect

Cori Hendon

Technical Solutions
Delivery Director

Miss the event? Watch the recording:

Product Recommender Systems

Part 1: Attribute Similarity

A lot of times people don’t know what they want until you show it to them.

Recommender systems have revolutionized the way industry leaders interact with their customers. Not only has it vastly increased sales for trailblazing companies like Netflix and Amazon, but it makes customers feel known and understood, which is the number one desire for consumers when shopping today. Netflix gains 80% of its total watch time and saves $1 billion a year thanks to its recommender system. Amazon derives 35% of its revenue from the same type of recommendation algorithms. But there’s a place for all retailers at the table when it comes to using these systems to give your customers what they want.

Whether it’s to add an “other customers bought” or “popular items” section to you site – both shown to be vastly successful for upselling customers, or sending customers email and ad offers using algorithms based on their purchasing history – we’re here to show you how to implement one of the most popular machine learning tactics businesses use to drive personalization and increase customer loyalty.