TwERC: High Performance Ensembled Candidate Generation for Ads Recommendation at Twitter

02/27/2023
by   Vanessa Cai, et al.
18

Recommendation systems are a core feature of social media companies with their uses including recommending organic and promoted contents. Many modern recommendation systems are split into multiple stages - candidate generation and heavy ranking - to balance computational cost against recommendation quality. We focus on the candidate generation phase of a large-scale ads recommendation problem in this paper, and present a machine learning first heterogeneous re-architecture of this stage which we term TwERC. We show that a system that combines a real-time light ranker with sourcing strategies capable of capturing additional information provides validated gains. We present two strategies. The first strategy uses a notion of similarity in the interaction graph, while the second strategy caches previous scores from the ranking stage. The graph based strategy achieves a 4.08 strategy achieves a 1.38 complement both the light ranker and one another. Finally, we describe a set of metrics that we believe are valuable as a means of understanding the complex product trade offs inherent in industrial candidate generation systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/12/2022

kNN-Embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval

Candidate generation is the first stage in recommendation systems, where...
research
09/12/2019

Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation

Generating the Top-N recommendations from a large corpus is computationa...
research
07/12/2023

Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking

Dividing ads ranking system into retrieval, early, and final stages is a...
research
05/13/2021

Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter

Traditionally, heuristic methods are used to generate candidates for lar...
research
03/02/2022

An Effective Way for Cross-Market Recommendation with Hybrid Pre-Ranking and Ranking Models

The Cross-Market Recommendation task of WSDM CUP 2022 is about finding s...
research
04/29/2023

Beyond Prediction: On-street Parking Recommendation using Heterogeneous Graph-based List-wise Ranking

To provide real-time parking information, existing studies focus on pred...
research
05/20/2020

Contrastive Learning for Debiased Candidate Generation at Scale

Deep candidate generation has become an increasingly popular choice depl...

Please sign up or login with your details

Forgot password? Click here to reset