Skip to main content
Uber logo

Schedule rides in advance

Reserve a rideReserve a ride

Schedule rides in advance

Reserve a rideReserve a ride
AI

Scaling Uber’s Customer Support Ticket Assistant (COTA) System with Deep Learning

August 23, 2018 / Global
Featured image for Scaling Uber’s Customer Support Ticket Assistant (COTA) System with Deep Learning
Figure 1. (a) The model architecture of COTA v1 leverages topic modeling, traditional feature engineering techniques, and a point-wise ranking algorithm, while (b) COTA v2 supports a deep learning architecture with a mixture of input features.
Figure 2. t-SNE plots depict embeddings learned by deep learning models for a) words and b) contact types.
Figure 3. We built a deep learning Spark Pipeline architecture for a) training models and b) serving requests.
Figure 4. Our model lifecycle management pipeline consists of six jobs, including Data ETL, Spark Transformations, and Model Merging.
Figure 5. Overall test strategy to compare the COTA v1 and COTA v2 systems.
Figure 6. Key metrics from online test: a) model accuracy and b) average handle time during both A/A and A/B tests on a daily basis.
Huaixiu Zheng

Huaixiu Zheng

Huaixiu Zheng is a senior data scientist at Uber, working on projects in the domains of deep learning, reinforcement learning, natural language processing and conversational AI systems.

Guoqin Zheng

Guoqin Zheng

Guoqin Zheng is a senior machine learning engineer on Uber's Michelangelo team.

Naveen Somasundaram

Naveen Somasundaram

Naveen Somasundaram is a senior machine learning engineer on Uber's Michelangelo team.

Basab Maulik

Basab Maulik

Basab Maulik is a senior software engineer on Uber's Customer Obsession team.

Hugh Williams

Hugh Williams

Hugh Williams is a data science manager on Uber's Applied Machine Learning team.

Jeremy Hermann

Jeremy Hermann

Jeremy Hermann is an engineering manager on Uber's Michelangelo team.

Posted by Huaixiu Zheng, Guoqin Zheng, Naveen Somasundaram, Basab Maulik, Hugh Williams, Jeremy Hermann

Category: