Generating Purpose-Driven Explanations: The Case of Process Predictive Model Inspection

Wickramanayake, B; Ouyang, C; Moreira, C; Xu, Y

Generating Purpose-Driven Explanations: The Case of Process Predictive Model Inspection

Wickramanayake, B Ouyang, C Moreira, C Xu, Y

Permalink

Publisher:: Springer
Publication Type:: Conference Proceeding
Citation:: International Journal of Intelligent Information and Database Systems, 2022, 452, pp. 120-129
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	978-3-031-07481-3_14.pdf	Published version	3.06 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wickramanayake, B
dc.contributor.author	Ouyang, C
dc.contributor.author	Moreira, C
dc.contributor.author	Xu, Y
dc.date	2022-06-06
dc.date.accessioned	2023-06-30T23:33:15Z
dc.date.available	2023-06-30T23:33:15Z
dc.date.issued	2022-01-01
dc.identifier.citation	International Journal of Intelligent Information and Database Systems, 2022, 452, pp. 120-129
dc.identifier.isbn	978-3-031-07480-6
dc.identifier.issn	1751-5858
dc.identifier.issn	1865-1356
dc.identifier.uri	http://hdl.handle.net/10453/171059
dc.description.abstract	Explainable AI is an emerging branch of data science that focuses on demystifying the complex computation logic of machine learning with an aim to improve the transparency, validity and trust in automated decisions. While existing research focuses on building methods and techniques to explain ‘black-box’ models, much attention has not been paid to generating model explanations. Effective model explanations are often driven by the purpose of explanation in a given problem context. In this paper, we propose a framework to support generating model explanations for the purpose of model inspection in the context of predictive process analytics. We build a visual explanation platform as an implementation of the proposed framework for inspecting and analysing a process predictive model, and demonstrate the applicability of the framework using a real-life case study on a loan application process.
dc.language	en
dc.publisher	Springer
dc.relation.ispartof	International Journal of Intelligent Information and Database Systems
dc.relation.ispartof	International Conference on Advanced Information Systems Engineering
dc.relation.ispartofseries	Lecture Notes in Business Information Processing
dc.relation.isbasedon	10.1007/978-3-031-07481-3_14
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0804 Data Format, 0806 Information Systems
dc.title	Generating Purpose-Driven Explanations: The Case of Process Predictive Model Inspection
dc.type	Conference Proceeding
utslib.citation.volume	452
utslib.location.activity	Leuven, Belgium
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0804 Data Format
utslib.for	0806 Information Systems
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Provost
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-06-30T23:33:13Z
pubs.finish-date	2022-06-10
pubs.place-of-publication	Switzerland
pubs.publication-status	Published
pubs.start-date	2022-06-06
pubs.volume	452
dc.location	Switzerland

Abstract:

Explainable AI is an emerging branch of data science that focuses on demystifying the complex computation logic of machine learning with an aim to improve the transparency, validity and trust in automated decisions. While existing research focuses on building methods and techniques to explain ‘black-box’ models, much attention has not been paid to generating model explanations. Effective model explanations are often driven by the purpose of explanation in a given problem context. In this paper, we propose a framework to support generating model explanations for the purpose of model inspection in the context of predictive process analytics. We build a visual explanation platform as an implementation of the proposed framework for inspecting and analysing a process predictive model, and demonstrate the applicability of the framework using a real-life case study on a loan application process.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/171059