Exploration with Model Uncertainty at Extreme Scale in Real-Time Bidding

Abstract

In this work, we present a scalable and efficient system for exploring the supply landscape in real-time bidding. The system directs exploration based on the predictive uncertainty of models used for click-through rate prediction and works in a high-throughput, low-latency environment. Through online A/B testing, we demonstrate that exploration with model uncertainty has a positive impact on model performance and business KPIs.

References in corpus (1)

• Scaling TensorFlow to 300 million predictions per second