Key Learning Outcomes

ML Engineers & Data Scientists

who are in charge of defining the technical aspects of recommender systems or building the end-to-end serving infrastructure for recommender systems

Think critically about the possible approaches to designing a recommender system and the pros/cons of each.
Choose an optimal approach to a given recommender system depending on its requirements and constraints.
Understand the technical requirements of a recommender system in practice.

Product Managers

who are in charge of defining roadmaps and allocating resources to initiatives related to recommender systems.

Think critically about the possible impact of recommender systems and the expected outcome of the different approaches under different constraints.
Propose a credible roadmap to introduce (or improve) recommender systems into complex products.
Understand detailed technical proposals for recommender systems, including pros/cons, requirements, and need for resource allocation.

Watch Xavier's recent live chat on

What's changed in rec systems?

Meet Your


Deepak Agarwal

Senior Engineering Leader at Pinterest

Deepak Agarwal (Ph.D) is VP of engineering at Pinterest, where he leads all engineering that power user experiences on the Pinterest app and browser. Prior to this, he was 
VP of AI at LinkedIn, where he established an AI/ML org and scaled it from 2 to 500+ in 8 years. He began his technical career in recommender systems at Yahoo! Research and deployed one of the first recommender systems for web applications personalizing the Yahoo! front page with an improvement of 300% over 2 years. He has over 100+ research publications, 6000+ citations, 50+ patents (issued) and has published a book on Recommender Systems for practitioners. He began his career as a statistician and is a Fellow of the American Statistical Association.

Xavier Amatriain

Co-Founder & CTO and Curai

Xavier Amatriain (Ph.D.) is co-founder and CTO of Curai, a series B health tech startup. Previous to this, he led Engineering at Quora and was Research/Engineering Director at Netflix, where he started and led the Algorithms team building the famous Netflix recommendations. Prior to this, he was a researcher both in academia and industry. With over 100 research publications (and 5k citations), Xavier is best known for his work on AI and machine learning in general, and recommender systems in particular.

Want to get to know Professor Bernstein?

You’re invited to our live course information session

Professor Berstein is hosting a live 30 minute session free to attend for all. He will be giving a breif introduction to the his upcoming course and then answering audience questions.

4:00-4:30pm PST; March 15

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

About Xavier and Deepak’s

Live Cohort

Recommender systems and personalization have become essential components of successful digital products in recent years. Some authors even claim that we have transitioned from the “age of search” to the “age of recommendation” (Chris Anderson in “The Long Tail”). But, designing recommender systems in practice is not trivial. It requires not only understanding of state-of-the-art machine learning approaches, but also engineering (particularly for distributed systems), product design, experimentation and business analytics. In this course we will teach you how to think about all these aspects in order to understand the tradeoffs of different approaches and make the right decision for your application and business.

What are important considerations for recommender systems infrastructure in order to deploy a recommender system at scale?

How can I overcome the key challenges and opportunities ahead: ethical issues underlying modern day recommender systems and technical approaches, balancing personalization and privacy, and AI-based content generation with human in the loop?

Session 1 - Introduction to recommender systems: Basics and classic techniques

Wednesday, November 2
8 AM  (PST)

Learn the components, metrics, and classic design approaches of recommender systems.

Develop an understanding of the fundamental components and techniques behind modern recommender systems

Design a basic recommender system using classic approaches such as collaborative filtering or content based

Contrast classic approaches to recommendation by listing their pros and cons (e.g., cold-start)

Session 2 - Learning to rank and hybrid approaches to recommendation

Monday, November 7
8 AM  (PST)

Learn how ranking is an essential part of modern recommender systems and how to combine approaches in hybrid systems.

Develop an intuition of how ranking approaches work in practice.

Design a recommender system based on learning to rank approaches.

Use hybridization techniques to combine any of the approaches introduced so far

Session 3 - Other advanced approaches to recommending content

Wednesday, November 9
8 AM  (PST)

Introduce other state-of-the-art approaches to recommendations.

Introduce the explore/exploit dilemma in recommender systems and select the appropriate exploration/exploitation tradeoff by understanding multi-armed bandits and similar approaches.

Introduce contextual aspects/features to the recommender system by selecting the appropriate modeling approach.

Use deep learning for complex recommendations such as sequences, image, or text.

Session 4 - Recommender Systems in Industry I

Monday, November 14
8 AM  (PST)

The knowledge introduced in previous sessions will be illustrated with real-world examples of recommender systems in industry.

Contrast and differentiate the approaches to recommendation used at LinkedIn and Pinterest.

Understand and argue about the importance of ethics and fairness when designing a recommender system

Build an intuition for deep learning approaches to recommender systems that will be described in later sessions

Session 5 - Recommender Systems in Industry II

Wednesday, November 16
8 AM  (PST)

The knowledge introduced in previous sessions will be illustrated with real-world examples of recommender systems in industry.

Contrast and differentiate the approaches to recommendation used at Netflix and Quora.

Understand the role of UI components such as explanations in the design of a recommender system

Design an end-to-end recommender system infrastructure, from training to serving model results in real-time

Still have questions?

We’re here to help!

Do I have to attend all of the sessions live in real-time?

You don’t! We record every live session in the cohort and make each recording and the session slides available on our portal for you to access anytime.

Will I receive a certificate upon completion?

Each learner receives a certificate of completion, which is sent to you upon completion of the cohort (along with access to our Alumni portal!). Additionally, Sphere is listed as a school on LinkedIn so you can display your certificate in the Education section of your profile.!

Is there homework?

Throughout the cohort, there may be take-home questions that pertain to subsequent sessions. These are optional, but allow you to engage more with the instructor and other cohort members!

Can I get the course fee reimbursed by my company?

While we cannot guarantee that your company will cover the cost of the cohort, we are accredited by the Continuing Professional Development (CPD) Standards Office, meaning many of our learners are able to expense the course via their company or team’s L&D budget. We even provide an email template you can use to request approval.

I have more questions, how can I get in touch?

Please reach out to us via our Contact Form with any questions. We’re here to help!

Book a time to talk with the Sphere team