Skip to main content
Uber logo

Schedule rides in advance

Reserve a rideReserve a ride

Schedule rides in advance

Reserve a rideReserve a ride
Engineering, Uber AI

Innovative Recommendation Applications Using Two Tower Embeddings at Uber

26 July 2023 / Global
Featured image for Innovative Recommendation Applications Using Two Tower Embeddings at Uber
Image
Figure 1: Left graph describes how embeddings are generated from regular features; Right graph describe how embeddings can be used to find similar restaurants.
Image
Figure 2: Left image shows the architecture of eater-item two tower embedding model; Right images shows how we can use the two tower embeddings to find the most relevant restaurants for eaters. 
Image
Figure 3: A simplified graph on how Uber retrieval system SIA uses two tower embedding to fetch most relevant restaurants for Eats homefeed ranking.
Image
Figure 4
Image
Figure 5: A sketch graph to show how the layer sharing plays role in two tower model
Image
Figure 6: E2E pipeline flow that shows how the two embeddings are used in uber eats recommender system
Bo Ling

Bo Ling

Bo Ling is a Staff Software Engineer on Uber’s AI Platform team. He works on NLP, Large language models and recommendation systems. He is the leading engineer on embedding models and LLM in the team.

Melissa Barr

Melissa Barr

Melissa Barr is a Senior Technical Program Manager on Uber’s AI Platform team. She is based in New York City. She drives a broad set of programs across ML & AI, specializing in topics with embeddings, recommendation systems, and large language models.

Dhruva Dixith Kurra

Dhruva Dixith Kurra

Dhruva Dixith Kurra is a Senior Machine Learning Engineer on Uber's AI platform team in the San Francisco Bay area. He specializes in training and deploying large-scale recommendation systems, ads systems, NLP systems, and large language models, contributing to the advancement of Uber's business through machine learning techniques.

Chun Zhu

Chun Zhu

Chun Zhu is a Senior Software Engineer on the Uber AI Platform team based in the San Francisco Bay area.

Nicholas Marcott

Nicholas Marcott

Nicholas Brett Marcott is a Staff Software Engineer, TLM on the Uber AI Feature Store team in the San Francisco Bay area. He specializes in serving data for ML models at high scale.

Posted by Bo Ling, Melissa Barr, Dhruva Dixith Kurra, Chun Zhu, Nicholas Marcott