Mining actionable behavioral rules

Peng Su, Wenji Mao, Dajun Zeng, Huimin Zhao

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Many applications can benefit from constructing models to predict the behavior of an entity. However, such models do not provide the user with explicit knowledge that can be directly used to influence (restrain or encourage) behavior for the user's interest. Undoubtedly, the user often exactly needs such knowledge. This type of knowledge is called actionable knowledge. Actionability is a very important criterion measuring the interestingness of mined patterns. In this paper, to mine such knowledge, we take a first step toward formally defining a new class of data mining problem, named actionable behavioral rule mining. Our definition explicitly states the problem as a search problem in a framework of support and expected utility. We also propose two algorithms for mining such rules. Our experiment shows the validity of our approach, as well as the practical value of our defined problem.

Original languageEnglish (US)
Pages (from-to)142-152
Number of pages11
JournalDecision Support Systems
Volume54
Issue number1
DOIs
StatePublished - Dec 2012

Fingerprint

Data Mining
Data mining
Experiments

Keywords

  • Actionable behavioral rule
  • Actionable knowledge discovery
  • Data mining

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Information Systems and Management
  • Arts and Humanities (miscellaneous)
  • Developmental and Educational Psychology

Cite this

Mining actionable behavioral rules. / Su, Peng; Mao, Wenji; Zeng, Dajun; Zhao, Huimin.

In: Decision Support Systems, Vol. 54, No. 1, 12.2012, p. 142-152.

Research output: Contribution to journalArticle

Su, Peng ; Mao, Wenji ; Zeng, Dajun ; Zhao, Huimin. / Mining actionable behavioral rules. In: Decision Support Systems. 2012 ; Vol. 54, No. 1. pp. 142-152.
@article{eb2145ea9c4c4aa883c22129085e6aca,
title = "Mining actionable behavioral rules",
abstract = "Many applications can benefit from constructing models to predict the behavior of an entity. However, such models do not provide the user with explicit knowledge that can be directly used to influence (restrain or encourage) behavior for the user's interest. Undoubtedly, the user often exactly needs such knowledge. This type of knowledge is called actionable knowledge. Actionability is a very important criterion measuring the interestingness of mined patterns. In this paper, to mine such knowledge, we take a first step toward formally defining a new class of data mining problem, named actionable behavioral rule mining. Our definition explicitly states the problem as a search problem in a framework of support and expected utility. We also propose two algorithms for mining such rules. Our experiment shows the validity of our approach, as well as the practical value of our defined problem.",
keywords = "Actionable behavioral rule, Actionable knowledge discovery, Data mining",
author = "Peng Su and Wenji Mao and Dajun Zeng and Huimin Zhao",
year = "2012",
month = "12",
doi = "10.1016/j.dss.2012.04.013",
language = "English (US)",
volume = "54",
pages = "142--152",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Mining actionable behavioral rules

AU - Su, Peng

AU - Mao, Wenji

AU - Zeng, Dajun

AU - Zhao, Huimin

PY - 2012/12

Y1 - 2012/12

N2 - Many applications can benefit from constructing models to predict the behavior of an entity. However, such models do not provide the user with explicit knowledge that can be directly used to influence (restrain or encourage) behavior for the user's interest. Undoubtedly, the user often exactly needs such knowledge. This type of knowledge is called actionable knowledge. Actionability is a very important criterion measuring the interestingness of mined patterns. In this paper, to mine such knowledge, we take a first step toward formally defining a new class of data mining problem, named actionable behavioral rule mining. Our definition explicitly states the problem as a search problem in a framework of support and expected utility. We also propose two algorithms for mining such rules. Our experiment shows the validity of our approach, as well as the practical value of our defined problem.

AB - Many applications can benefit from constructing models to predict the behavior of an entity. However, such models do not provide the user with explicit knowledge that can be directly used to influence (restrain or encourage) behavior for the user's interest. Undoubtedly, the user often exactly needs such knowledge. This type of knowledge is called actionable knowledge. Actionability is a very important criterion measuring the interestingness of mined patterns. In this paper, to mine such knowledge, we take a first step toward formally defining a new class of data mining problem, named actionable behavioral rule mining. Our definition explicitly states the problem as a search problem in a framework of support and expected utility. We also propose two algorithms for mining such rules. Our experiment shows the validity of our approach, as well as the practical value of our defined problem.

KW - Actionable behavioral rule

KW - Actionable knowledge discovery

KW - Data mining

UR - http://www.scopus.com/inward/record.url?scp=84868649039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868649039&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2012.04.013

DO - 10.1016/j.dss.2012.04.013

M3 - Article

AN - SCOPUS:84868649039

VL - 54

SP - 142

EP - 152

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

IS - 1

ER -