Optimized bidding algorithm of real time bidding in online ads auction

Abstract

RTB is one of the most popular topics on online advertising in recent years; RTB-based ads auction subverts traditional advertising strategy, explicitly stating the concept that “advertisement is commodity”. Most of the current researches on online ads auction focus at the point of linear programming or assignment problem, while there's little study on the macro-level auction mechanism, especially the characteristics of the general winning bids. Based on real log data from a DSP in China, this paper conducts empirical analysis of average deal price and bidding volume at different times of impressions. Finally, we design an optimized method for delivery of RTB ads through offline experiments.