# OCC: A Smart Reply System for Efficient In-App Communications

## TL;DR

This paper presents Uber's OCC, a smart reply system for in-app messaging that uses machine learning for intent detection and reply retrieval, enabling quick responses and high adoption among drivers.

## Contribution

The paper introduces a scalable, efficient smart reply system tailored for mobile chat, combining intent detection with reply retrieval, and demonstrates its successful deployment in Uber's app.

## Key findings

- Achieved 76% accuracy in intent detection.
- 71% of rider-driver messages used smart replies in production.
- System performs comparably to deep learning methods with less training data.

## Abstract

Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber's smart reply system: one-click-chat (OCC), which is a key enhanced feature on top of the Uber in-app chat system. It enables driver-partners to quickly respond to rider messages using smart replies. The smart replies are dynamically selected according to conversation content using machine learning algorithms. Our system consists of two major components: intent detection and reply retrieval, which are very different from standard smart reply systems where the task is to directly predict a reply. It is designed specifically for mobile applications with short and non-canonical messages. Reply retrieval utilizes pairings between intent and reply based on their popularity in chat messages as derived from historical data. For intent detection, a set of embedding and classification techniques are experimented with, and we choose to deploy a solution using unsupervised distributed embedding and nearest-neighbor classifier. It has the advantage of only requiring a small amount of labeled training data, simplicity in developing and deploying to production, and fast inference during serving and hence highly scalable. At the same time, it performs comparably with deep learning architectures such as word-level convolutional neural network. Overall, the system achieves a high accuracy of 76% on intent detection. Currently, the system is deployed in production for English-speaking countries and 71% of in-app communications between riders and driver-partners adopted the smart replies to speedup the communication process.