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

TL;DR

This paper introduces a scalable real-time bidding system that uses model uncertainty to guide exploration, improving click-through rate predictions and business KPIs in high-throughput environments.

Contribution

It presents a novel system leveraging model uncertainty for exploration in real-time bidding, optimized for high scalability and low latency.

Findings

Exploration with model uncertainty improves model performance.

Online A/B tests show positive impact on business KPIs.

System operates efficiently at extreme scale.

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.