Developing data mining methods for finding causal relationships involving multiple factors /
Files
(Published version)
Date
2017
Authors
Ma, Saisai,
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
thesis
Citation
Statement of Responsibility
Conference Name
Abstract
In the past decades, causal discovery from observational data has been studied widely. However, most existing research has focused on detecting causal relationship between a single factor and the outcome, which may not be sufficient for reasoning about the cause of a particular effect. In this thesis, we study complex causal relationships with multiple factors involved, and have developed the methods for discovering combined causes, cause interactions and context specific causes from data. We have also developed a causality based classification model for predictions with causal interpretations.
School/Discipline
University of South Australia. School of Information Technology and Mathematical Sciences.
School of Information Technology and Mathematical Sciences.
School of Information Technology and Mathematical Sciences.
Dissertation Note
Thesis (PhD(Computer and Information Science))--University of South Australia, 2017.
Provenance
Copyright 2017 Saisai Ma.
Description
1 ethesis (ix, 9 unnumbered pages, 183 pages) :
illustrations
Includes bibliographical references (pages 168-183)
illustrations
Includes bibliographical references (pages 168-183)
Access Status
506 0#$fstar $2Unrestricted online access