Unpacking how Ads Ranking Works @Pinterest

QCon San Francisco 2023

Session Recommender Systems

Unpacking how Ads Ranking Works @Pinterest

Monday Oct 2 / 05:05PM PDT, Ballroom BC

Abstract

In this session, we delve into the dynamic world of social media advertising. Facebook, Snap, Pinterest, Twitter, and many others generate the majority of their revenue from targeted ads. We will unpack how Pinterest harnesses the power of Deep Learning Models and big data to tailor relevant advertisements to the pinners. Enjoy a comprehensive walkthrough of the entire advertising funnel and the sophisticated Ads Serving Architecture, before diving deeper into the construction of Deep Learning Models for highly responsive and personalized ads. We will further discuss the challenges faced in industrial-scale models creation and how to meet low-latency requests. Join us as we unravel the complex algorithmic models that fuel social media advertising.

Interview

My current focus is around privacy-safe recommendation systems and ensuring we help bring pinners the inspiration to action by providing the most relevant content. 

The field of Ads Recommendation is intricate, and I aim to elucidate its complexities while facilitating a better understanding of how advertising systems operate in general.

The target audience is developers and practitioners, who have a basic understanding of practical machine learning and system building.

To gain insight into the amalgamation of Machine Learning that enables the delivery of personalized and pertinent content, powering the feed of numerous popular applications.

Topics

Recommender Systems AI/ML ML systems
76% senior dev or higher
1:11 speaker ratio
60+ practitioners

QCon San Francisco 2023 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.

Share

From the same track

Monday 2 October

10:35 Ballroom BC Session Serverless AWS Lambda Under the Hood Mike Danilov Senior Principal Engineer @AWS Lambda 11:45 Ballroom BC Session Database Relational Data at the Edge Justin Kwan, Vignesh Ravichandran 13:35 Ballroom BC Session K8s NIST 800-207A: Implementing Zero Trust Architecture Zack Butcher Founding Engineer @Tetrateio & NIST co-author on security, prev core services @GoogleCloud 14:45 Ballroom BC Session Distributed Systems Managing 238M Memberships at Netflix Surabhi Diwan Senior Software Engineer @Netflix 15:55 Seacliff D Unconference Unconference: Architectures You've Always Wondered About 17:05 Ballroom BC Session Recommender Systems Unpacking how Ads Ranking Works @Pinterest Aayush Mudgal Senior Machine Learning Engineer @Pinterest, Focusing on Privacy Safe Recommender Systems, IIT Kanpur Alumnus