Score Look-Alike Audiences

Look-alike models, which are efficient tools for finding similar users from a smaller user set, are quickly revolutionizing the online programmatic advertising industry. The datasets in these contexts exhibit extremely sparse feature spaces on a massive scale, so traditionally, the state-of-the-art...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiang Ma, Wagh, Eeshan, Jiayi Wen, Zhen Xia, Ormandi, Robert, Datong Chen
Format: Conference Proceeding
Language:English
Subjects:
Advertising
Approximation algorithms
Computational modeling
Context
Context modeling
Data models
Industries
look-alike model
online advertising
spark
user ranking
user scoring
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Look-alike models, which are efficient tools for finding similar users from a smaller user set, are quickly revolutionizing the online programmatic advertising industry. The datasets in these contexts exhibit extremely sparse feature spaces on a massive scale, so traditionally, the state-of-the-art look-alike models have used pairwise similarities to construct these similar user sets. One of the key challenges of the similarity-based models is that they do not provide a way to measure the potential value of the users to an advertiser, which is crucial in an advertising context. We propose methods to score users within the expanded audience in a way which relates directly to the business metric that the advertiser wants to optimize. We present three scoring models and show that, through empirical evaluation using real-world, large-scale data, by incorporating the potential value of a user to an advertiser into our scoring model, we can significantly improve the performance of the look-alike models over methods which only use pairwise similarities of users.
ISSN:2375-9259
DOI:10.1109/ICDMW.2016.0097