Authors:
Jian Yang
1
;
Erik Vee
1
;
Sergei Vassilvitskii
1
;
John Tomlin
2
;
Jayavel Shanmugasundaram
3
;
Tasos Anastasakos
1
and
Oliver Kennedy
4
Affiliations:
1
Yahoo! Labs, United States
;
2
Yahoo! Labs and Marketshare LLC, United States
;
3
Yahoo! Labs and Google, United States
;
4
Cornell University and EPFL, United States
Keyword(s):
Advertising, Inventory allocation, Multi-objective optimization.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Methodologies and Technologies
;
Operational Research
;
Optimization
;
Resource Allocation
;
Symbolic Systems
Abstract:
We discuss a multi-objective/goal programming model for the allocation of inventory of graphical advertisements.
The model considers two types of campaigns: guaranteed delivery (GD), which are sold months in
advance, and non-guaranteed delivery (NGD), which are sold using real-time auctions. We investigate various
advertiser and publisher objectives such as (a) revenue from the sale of user visits, clicks and conversions,
(b) future revenue from the sale of NGD inventory, and (c) “fairness” of allocation. While the first two objectives
are monetary, the third is not. This combination of demand types and objectives leads to potentially
many variations of our model, which we delineate and evaluate. Our experimental results, which are based on
optimization runs using real data sets, demonstrate the effectiveness and flexibility of the proposed model.