Fast Demand Learning for Display Advertising Revenue Management
نویسندگان
چکیده
The present paper is motivated by the network revenue management problems that occur in online display advertising. In this setting, each impression (demand) type corresponds to a vector of d user features; consequently, the overall number of demand types that need to be forecast is exponential in d. Our main contribution is to show that such high dimensional demand spaces can still be estimated efficiently. In particular, using a number of demand samples that scales linearly in d and quadratically in the number of advertisers, we construct a demand estimator that informs a simple bid-price allocation policy. We show that this policy garners at least a (1− ) fraction of the optimal revenues that could be achieved with perfect a priori information of the demand type distribution.
منابع مشابه
Dynamic Revenue Management for Online Display Advertising
In this paper, we propose an dynamic optimization model to maximize a web publisher’s online display advertising revenues. Specifically, our model dynamically selects which advertising requests to accept and dynamically delivers the promised advertising impressions to viewers so as to maximize revenue, accounting for uncertainty in advertising requests and website traffic. After characterizing ...
متن کاملPerformance Based Display Advertising - A Large Scale Machine Learning Model in Practice
Display advertising is evolving from just selling eye balls to demographic segments, as in traditional print media, to performance based systems where advertisers have an ability to pay for the type of user response valuable to them. Depending on who owns the risk of variance in user response, the advertisers have multiple pricing types options to run their advertising campaign on. These includ...
متن کاملDisplay Advertising with Real-Time Bidding (RTB) and Behavioural Targeting
In display and mobile advertising, the most significant progress in recent years is the employment of the so-called Real-Time Bidding (RTB) mechanism to buy and sell ads. RTB essentially facilitates buying an individual ad impression in real time while it is still being generated from a user’s visit. RTB not only scales up the buying process by aggregating a large amount of available inventorie...
متن کاملDo Online Social Networks Increase Welfare?
We consider a strategic online social network that controls information flows between agents in a social learning setting. Agents on the network select among products of competing firms of unknown quality. The network sells advertising to firms. We consider display advertising, which is standard firm-to-consumer advertising, and social advertising, in which agents who purchased that firm’s prod...
متن کاملPosted price programmatic guarantee in display advertising
This paper presents a revenue maximisation model for sales channel allocation based on dynamic programming. It helps the media seller to determine how to distribute the sales volume of page views between guaranteed and nonguaranteed channels for display advertising. The model can algorithmically allocate and price the future page views via standardised guaranteed contracts in addition to real-t...
متن کامل