Learning in imbalanced relational data

Traditional learning techniques learn from flat data files with the assumption that each class has a similar number of examples. However, the majority of real-world data are stored as relational systems with imbalanced data distribution, where one class of data is over-represented as compared with o...

Full description

Bibliographic Details
Main Authors: Ghanem, Amal, Venkatesh, Svetha, West, Geoff
Other Authors: M. Ejiri
Format: Conference Paper
Published: IAPR 2008
Online Access:http://hdl.handle.net/20.500.11937/2826
_version_ 1848744059698413568
author Ghanem, Amal
Venkatesh, Svetha
West, Geoff
author2 M. Ejiri
author_facet M. Ejiri
Ghanem, Amal
Venkatesh, Svetha
West, Geoff
author_sort Ghanem, Amal
building Curtin Institutional Repository
collection Online Access
description Traditional learning techniques learn from flat data files with the assumption that each class has a similar number of examples. However, the majority of real-world data are stored as relational systems with imbalanced data distribution, where one class of data is over-represented as compared with other classes. We propose to extend a relational learning technique called Probabilistic Relational Models (PRMs) to deal with the imbalanced class problem. We address learning from imbalanced relational data using an ensemble of PRMs and propose a new model: the PRMs-IM. We show the performance of PRMs-IM on a real university relational database to identify students at risk.
first_indexed 2025-11-14T05:55:27Z
format Conference Paper
id curtin-20.500.11937-2826
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T05:55:27Z
publishDate 2008
publisher IAPR
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-28262022-11-21T05:19:38Z Learning in imbalanced relational data Ghanem, Amal Venkatesh, Svetha West, Geoff M. Ejiri R. Kasturi G. Sanniti di Baja Traditional learning techniques learn from flat data files with the assumption that each class has a similar number of examples. However, the majority of real-world data are stored as relational systems with imbalanced data distribution, where one class of data is over-represented as compared with other classes. We propose to extend a relational learning technique called Probabilistic Relational Models (PRMs) to deal with the imbalanced class problem. We address learning from imbalanced relational data using an ensemble of PRMs and propose a new model: the PRMs-IM. We show the performance of PRMs-IM on a real university relational database to identify students at risk. 2008 Conference Paper http://hdl.handle.net/20.500.11937/2826 10.1109/ICPR.2008.4761095 IAPR restricted
spellingShingle Ghanem, Amal
Venkatesh, Svetha
West, Geoff
Learning in imbalanced relational data
title Learning in imbalanced relational data
title_full Learning in imbalanced relational data
title_fullStr Learning in imbalanced relational data
title_full_unstemmed Learning in imbalanced relational data
title_short Learning in imbalanced relational data
title_sort learning in imbalanced relational data
url http://hdl.handle.net/20.500.11937/2826