Recommender Systems Best Practices

Learn insights from leaders and technical experts at global companies such as The New York Times, Tencent, Meituan, NVIDIA, and more.

Discover Practical Insights and Advice

Building, deploying, and optimizing recommender systems that effectively engages users and impacts business value, including revenue, is hard. Data scientists, machine learning engineers, and leads within global e-commerce, media, and on-demand domains have successfully designed, built, and deployed recommendation systems that impact business value. Download this paper to get insights, best practices, and advice from expert interviews and uncover how recommender systems teams handle preprocessing, feature engineering, training models, evaluating models, selecting which appropriate technologies to integrate, interoperability with open source, and more. 

A few featured leaders and experts interviewed include:

Monica Rogati

AI and Data Science Advisor, Creator of the first ML Model for LinkedIn's "People You Know" Feature

Xiangting Kong

Expert Engineer, Tencent

Chris Wiggins

Chief Data Scientist, The New York Times

Jun Huang

Senior Technical Expert, Meituan

Felipe Contratres

Tribe Leader of Personalization, Magalu (Magazine Luiza)

Vinny DeGenova

Associate Director of Data Science - Search & Recommendations, Wayfair

Even Oldridge

NVIDIA Merlin™ Engineering Lead, NVIDIA

Brief history of recommender systems

Recommender Systems in the Making

Read a brief history of recommender systems, including the people that built them, illustrating the evolution from the 1970s to the present.

Latest trends for global recommender systems

What’s Trending

Learn about the latest trends for global recommender systems in e-commerce, media, news, on-demand, and more.

Recommender systems practices

Best Practices

Hear from industry leaders about their recommender systems practices, including what they do to optimize recommenders.


Enterprise Content
Developer Content