Machine Learning
Rank aggregation methods for the Web
Proceedings of the 10th international conference on World Wide Web
Machine Learning
Ranking-based clustering of heterogeneous information networks with star network schema
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
A contextual-bandit approach to personalized news article recommendation
Proceedings of the 19th international conference on World wide web
Graph regularized transductive classification on heterogeneous information networks
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part I
Ranking-based classification of heterogeneous information networks
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Position-normalized click prediction in search advertising
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Multiview hierarchical bayesian regression model andapplication to online advertising
Proceedings of the 21st ACM international conference on Information and knowledge management
| Hi-index | 0.00 |
We present an algorithm which adapts a graph-based ranking model to the context of the problem of improving the process of serving advertisements to users. We transform the ad-based clickstream data into a heterogeneous graph model which respects differences in feature types (e.g. geolocation features, or browser-history features). The heterogeneous network model generates meaningful rankings of features which are predictive for each ad, as demonstrated by our classifier's performance. We also discuss how, in addition to serving as the basis for a classifier, this model may also provide an informative view of the data, which is not possible with black-box approaches, and which therefore makes it very suitable to the problem space of targeted ad serving.