Sign inSign up
Query Clustering based on Bid Landscape for Sponsored Search Auction Optimization thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Query Clustering based on Bid Landscape for Sponsored Search Auction Optimization

Published on Sep 27, 20134726 Views

Ye Chen

In sponsored search auctions, the auctioneer operates the marketplace by setting a number of auction parameters such as reserve prices for the task of auction optimization. The auction parameters may

KDD 2013 - Chicago

Related categories

Data MiningKnowledge Extraction

Chapter list

Query Clustering based on Bid Landscape for Sponsored Search Auction Optimization00:00
Summary00:42
Introduction: Sponsored Search02:55
Introduction: Example and Notations03:28
Introduction: GSP Auction04:34
Introduction: Auction Optimization07:46
Motivation10:24
Clustering Gaussian Densities12:16
Clustering Results (Gaussian)13:01
Model Assumption: Gaussian?13:48
A Better Assumption: GMM14:19
Hypothesis Test (“lottery results”)15:05
Hypothesis Test (“online shopping”)15:41
Clustering GMM Densities15:45
Learning GMM (per-query)16:53
Learning GMM (empirical evidence)17:27
Learning GMM (more evidence)18:09
Deriving the EM Algorithm (GMM)18:17
The EM Algorithm (GMM)18:32
Clustering Results (GMM)19:00
Results19:36
Acknowledgments20:44