Revenue Optimization with Approximate Bid Predictions
This provides a formal link between revenue optimization and standard machine learning models for advertisers and auction platforms, though it is incremental in applying existing prediction methods.
The paper tackles the challenge of setting reserve prices in advertising auctions by reducing the problem to prediction under squared loss, showing that the revenue gap is bounded by the predictor's average loss.
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.