Revenue Optimization with Approximate Bid Predictions

Abstract

In the context of advertising auctions, finding good reserve prices is a notoriously challenging learning problem. This is due to the heterogeneity of ad opportunity types and the non-convexity of the objective function. In this work, we show how to reduce reserve price optimization to the standard setting of prediction under squared loss, a well understood problem in the learning community. We further bound the gap between the expected bid and revenue in terms of the average loss of the predictor. This is the first result that formally relates the revenue gained to the quality of a standard machine learned model.

Accepted to NIPS 2017

References in corpus (2)

• Learning Simple Auctions
• The Sample Complexity of Revenue Maximization

Cited by in corpus (13)

• The Primal-Dual method for Learning Augmented Algorithms
• Learning Augmented Energy Minimization via Speed Scaling
• Regulatory Instruments for Fair Personalized Pricing
• Optimal Algorithms for Ski Rental with Soft Machine-Learned Predictions
• Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice
• Contextual Pandora's Box
• Adversarial learning for revenue-maximizing auctions
• Third-Party Data Providers Ruin Simple Mechanisms
• Learning to Clear the Market
• Can Q-Learning be Improved with Advice?
• Online Learning for Non-Stationary A/B Tests
• Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization
• Learning to Bid Without Knowing your Value