Scalable Online Ad Serving: Experimental Comparison of Simple Techniques
نویسندگان
چکیده
Online Ad Servers attempt to find the best ad to serve for a given triggering user event. The performance of the ad may be measured in several ways. We suggest a formulation in which the ad network is trying to maximize revenue subject to relevance constraints. We describe several simple algorithms for ad selection and review their complexity. We tested these algorithms using the Microsoft ad network from October 1 2006 to February 8 2007. Over 3 billion impressions, 9 million combinations of triggers with ads, and a number of algorithms were tested over this period. We discover curious differences between ad-servers aimed at revenue versus clickthrough rate.
منابع مشابه
Design and evaluation of two scalable protocols for location management of mobile nodes in location based routing protocols in mobile Ad Hoc Networks
Heretofore several position-based routing protocols have been developed for mobile ad hoc networks. Many of these protocols assume that a location service is available which provides location information on the nodes in the network.Our solutions decrease location update without loss of query success rate or throughput and even increase those.Simulation results show that our methods are effectiv...
متن کاملDesign and evaluation of two scalable protocols for location management of mobile nodes in location based routing protocols in mobile Ad Hoc Networks
Heretofore several position-based routing protocols have been developed for mobile ad hoc networks. Many of these protocols assume that a location service is available which provides location information on the nodes in the network.Our solutions decrease location update without loss of query success rate or throughput and even increase those.Simulation results show that our methods are effectiv...
متن کاملOffline Optimization for Online Ad Allocation
We consider online ad allocation from the perspective of optimizing delivery of a given set of ad reservations. Ad allocation naturally fits into the class of online bipartite matching problems: ad nodes are fixed, and impression (ad slot) nodes arrive one at a time, and must be assigned a qualified ad upon arrival. However most previous work on online matching does not model an important aspec...
متن کاملOptimal Online Frequency Capping Allocation using the Weight Approach
In this document, we present a simple approach for serving guaranteed delivery contracts with frequency capping which we call the weight method, which is optimal when targeting is user-dependent, as well as when there is no frequency caps. This methodology can also serve as a heuristic for more general problems. The method is consistent, in that the booking and planning methods work by simulati...
متن کاملComparing MicroRNA Target Gene Predictions Related to Alzheimer's Disease Using Online Bioinformatics Tools
Introduction: The prediction of microRNAs related to target genes using bioinformatics tools saves time and costs of the experimental analyses. In the present study, the prediction of microRNA target genes relevant to Alzheimer’s Diseases (AD) were compared with the experimentally reported data using different bioinformatics tools. Method: A total of 41 microRNAs associated with 21 essential ge...
متن کامل