The Data Scientist Show - Daliana Liu

Uber's ML Systems (Uber Eats, Customer Support), Declarative Machine Learning - Piero Molino - The Data Scientist Show #064

6 snips
Jul 4, 2023
Ask episode
AI Snips
Chapters
Transcript
Episode notes
ANECDOTE

Graph Neural Networks at Uber Eats

  • Piero worked on a graph neural network recommender for Uber Eats that incorporated multiple entities and weighted edges.
  • The embeddings reflected changes in user preferences after interactions, improving recommendations noticeably.
ANECDOTE

Uber's Customer Obsession System

  • The "Customer Obsession" ticket system reduced support handling time by 16% without harming customer satisfaction.
  • It used multi-task convolutional neural networks combining text data with user behavior and contextual features.
ADVICE

Balance Metrics with Business Goals

  • Always balance offline model metrics with online business metrics, especially customer satisfaction.
  • Use A/B tests to verify improvements and ensure no negative impact on important business KPIs.
Get the Snipd Podcast app to discover more snips from this episode
Get the app