Customer targeting models using actively-selected web content

Prem Melville*, Saharon Rosset, Richard D. Lawrence

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

We consider the problem of predicting the likelihood that a company will purchase a new product from a seller. The statistical models we have developed at IBM for this purpose rely on historical transaction data coupled with structured firmographic information like the company revenue, number of employees and so on. In this paper, we extend this methodology to include additional text-based features based on analysis of the content on each company's website. Empirical results demonstrate that incorporating such web content can significantly improve customer targeting. Furthermore, we present methods to actively select only the web content that is likely to improve our models, while reducing the costs of acquisition and processing.

Original languageEnglish
Title of host publicationKDD 2008 - Proceedings of the 14th ACMKDD International Conference on Knowledge Discovery and Data Mining
Pages946-953
Number of pages8
DOIs
StatePublished - 2008
Event14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008 - Las Vegas, NV, United States
Duration: 24 Aug 200827 Aug 2008

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008
Country/TerritoryUnited States
CityLas Vegas, NV
Period24/08/0827/08/08

Keywords

  • Active feature-value acquisition
  • Active learning
  • Text categorization
  • Web mining

Fingerprint

Dive into the research topics of 'Customer targeting models using actively-selected web content'. Together they form a unique fingerprint.

Cite this