۱- Introduction

۲- Related work

۳- Model

۴- Data and experimental settings

۵- Results

۶- Conclusion

References

Abstract

While page views are often sold instantly through real-time auctions when users visit websites, they can also be sold in advance via guaranteed contracts. In this paper, we present a dynamic programming model to study how an online publisher should optimally allocate and price page views between guaranteed and spot markets. The problem is challenging because the allocation and pricing of guaranteed contracts affect how advertisers split their purchases between the two markets, and the terminal value of the model is endogenously determined by the updated dual force of supply and demand in auctions. We take the advertisers’ purchasing behaviour into consideration, i.e., risk aversion and stochastic demand arrivals, and present a scalable and efficient algorithm for the optimal solution. The model is also empirically validated with a commercial dataset. The experimental results show that selling page views via both channels can increase the publisher’s expected total revenue, and the optimal pricing and allocation strategies are robust to different market and advertiser types.

Introduction

Display advertising is one of the most popular forms of online marketing. It uses the Internet and the World Wide Web as an advertising medium, and when users visit websites, the promotional messages (i.e., the ads), appear on the pages. They usually come in terms of rectangular images or photos placed on a web page either above, below or on the sides of the page’s main content and are linked to other web pages. Online publishers make profits by selling the page views, namely the impressions, through two channels: (i) selling them in advance via contracts; or (ii) auctioning them off in real time when users visit the web pages. The former is called guaranteed contracts (or reservation contracts) while the latter is called real-time bidding (RTB). Over the past decades, RTB has become the widely used sales model for display advertising, in which advertisers come to a common marketplace, i.e., ad exchange, to compete for impressions from their targeted users (Mansour, Muthukrishnan, & Nisan, 2012; Muthukrishnan, 2009).