Automatic Campaign Optimization for Online Advertising Using Return on Investment Metrics

Abstract

A method for optimizing quantitative return-on-investment performance in an online advertising campaign. The advertising campaign has a finite campaign period and a finite spending budget within a system that includes a bidding facility for bidding on a plurality of advertising slots. The method seeks to optimize performance of the campaign according to an objective function that includes a marginal return on investment variable, which variable is maintained throughout a series of iterations. Techniques are disclosed for capturing campaign parameters and constraints from advertisers, and mathematical techniques are used in determining a selected advertising slot upon which to bid at each iteration. A tracking system provides a history of winning bids and forecast of inventory. After bidding, the value of the marginal return on investment variable is changed based on the results of the bidding. The next bidding operations are based on the value of the marginal return on investment variable.

Dependencies are inferred from the claim text.