Using data mining methods to build customer profiles

Gediminas Adomavicius, Alexander Tuzhilin

Research output: Contribution to journalArticlepeer-review

169 Scopus citations

Abstract

An approach was developed that uses information from customers' transactional histories to construct individual profiles containing facts about the customer and rules describing that customer's behavior. A method was also established for validating customer's profiles to separate 'good' rules from 'bad'. The profile construction and validation methods were implemented using the 1:1Pro system.

Original languageEnglish (US)
Pages (from-to)74-81
Number of pages8
JournalComputer
Volume34
Issue number2
DOIs
StatePublished - Feb 2001

Fingerprint

Dive into the research topics of 'Using data mining methods to build customer profiles'. Together they form a unique fingerprint.

Cite this