RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance

Dennis Collaris; Mykola Pechenizkiy; Jarke J. van Wijk

doi:10.4230/OASIcs.Commit2Data.8

RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

16 Downloads (Pure)

Abstract

We conducted the RATE-Analytics project: a unique collaboration between Rabobank, Achmea, Tilburg and Eindhoven University. We aimed to develop foundations and techniques for next generation big data analytics. The main challenge of existing approaches is the lack of reliability and trustworthiness: if experts do not trust a model or its predictions they are much less likely to use and rely on that model. Hence, we focused on solutions to bring the human-in-the-loop, enabling the diagnostics and refinement of models, and support in decision making and justification. This chapter zooms in on the part of the project focused on developing explainable and trustworthy machine learning techniques.

Original language	English
Title of host publication	Commit2Data
Editors	Boudewijn R. Haverkort, Aldert de Jongste, Pieter van Kuilenburg, Ruben D. Vromans
Publisher	Schloss Dagstuhl - Leibniz-Zentrum für Informatik
Chapter	8
Pages	8:1-8:11
Number of pages	11
ISBN (Electronic)	978-3-95977-351-5
DOIs	https://doi.org/10.4230/OASIcs.Commit2Data.8
Publication status	Published - 28 Oct 2024

Publication series

Name	OpenAccess Series in Informatics (OASIcs)
Volume	124
ISSN (Electronic)	2190-6807

Funding

We would like to thank numerous colleagues of the RATE project team at Tilburg University, Rabobank, Achmea, and TU/e who over the years provided endless support and facilitated collaboration. We would like to thank NWO, Rabobank and Achmea for the provided funding. This work is part of the research programme Commit2Data, specifically the RATE Analytics project with project number 628.003.001. Last, but not least we would like to thank the reviewers for providing constructive feedback.

Funders	Funder number
Nederlandse Organisatie voor Wetenschappelijk Onderzoek	628.003.001
Tilburg University

Keywords

Visualization
Visual Analytics
Machine Learning
Interpretability
Explainability
XAI
Explain-ability

Access to Document

10.4230/OASIcs.Commit2Data.8

pdfFinal published version, 2.79 MBLicence: CC BY

Cite this

Collaris, D., Pechenizkiy, M., & van Wijk, J. J. (2024). RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance. In B. R. Haverkort, A. de Jongste, P. van Kuilenburg, & R. D. Vromans (Eds.), Commit2Data (pp. 8:1-8:11). (OpenAccess Series in Informatics (OASIcs); Vol. 124). Schloss Dagstuhl - Leibniz-Zentrum für Informatik. https://doi.org/10.4230/OASIcs.Commit2Data.8

Collaris, Dennis ; Pechenizkiy, Mykola ; van Wijk, Jarke J. / RATE-Analytics : Next Generation Predictive Analytics for Data-Driven Banking and Insurance. Commit2Data. editor / Boudewijn R. Haverkort ; Aldert de Jongste ; Pieter van Kuilenburg ; Ruben D. Vromans. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2024. pp. 8:1-8:11 (OpenAccess Series in Informatics (OASIcs)).

@inbook{a6156527b9a6461d904cb2a29a53ef40,

title = "RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance",

abstract = "We conducted the RATE-Analytics project: a unique collaboration between Rabobank, Achmea, Tilburg and Eindhoven University. We aimed to develop foundations and techniques for next generation big data analytics. The main challenge of existing approaches is the lack of reliability and trustworthiness: if experts do not trust a model or its predictions they are much less likely to use and rely on that model. Hence, we focused on solutions to bring the human-in-the-loop, enabling the diagnostics and refinement of models, and support in decision making and justification. This chapter zooms in on the part of the project focused on developing explainable and trustworthy machine learning techniques.",

keywords = "Visualization, Visual Analytics, Machine Learning, Interpretability, Explainability, XAI, Explain-ability",

author = "Dennis Collaris and Mykola Pechenizkiy and \{van Wijk\}, \{Jarke J.\}",

year = "2024",

month = oct,

day = "28",

doi = "10.4230/OASIcs.Commit2Data.8",

language = "English",

series = "OpenAccess Series in Informatics (OASIcs)",

publisher = "Schloss Dagstuhl - Leibniz-Zentrum f{\"u}r Informatik",

pages = "8:1--8:11",

editor = "Haverkort, \{Boudewijn R.\} and \{de Jongste\}, Aldert and \{van Kuilenburg\}, Pieter and Vromans, \{Ruben D.\}",

booktitle = "Commit2Data",

}

Collaris, D, Pechenizkiy, M & van Wijk, JJ 2024, RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance. in BR Haverkort, A de Jongste, P van Kuilenburg & RD Vromans (eds), Commit2Data. OpenAccess Series in Informatics (OASIcs), vol. 124, Schloss Dagstuhl - Leibniz-Zentrum für Informatik, pp. 8:1-8:11. https://doi.org/10.4230/OASIcs.Commit2Data.8

RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance. / Collaris, Dennis; Pechenizkiy, Mykola ; van Wijk, Jarke J.
Commit2Data. ed. / Boudewijn R. Haverkort; Aldert de Jongste; Pieter van Kuilenburg; Ruben D. Vromans. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2024. p. 8:1-8:11 (OpenAccess Series in Informatics (OASIcs); Vol. 124).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

TY - CHAP

T1 - RATE-Analytics

T2 - Next Generation Predictive Analytics for Data-Driven Banking and Insurance

AU - Collaris, Dennis

AU - Pechenizkiy, Mykola

AU - van Wijk, Jarke J.

PY - 2024/10/28

Y1 - 2024/10/28

N2 - We conducted the RATE-Analytics project: a unique collaboration between Rabobank, Achmea, Tilburg and Eindhoven University. We aimed to develop foundations and techniques for next generation big data analytics. The main challenge of existing approaches is the lack of reliability and trustworthiness: if experts do not trust a model or its predictions they are much less likely to use and rely on that model. Hence, we focused on solutions to bring the human-in-the-loop, enabling the diagnostics and refinement of models, and support in decision making and justification. This chapter zooms in on the part of the project focused on developing explainable and trustworthy machine learning techniques.

AB - We conducted the RATE-Analytics project: a unique collaboration between Rabobank, Achmea, Tilburg and Eindhoven University. We aimed to develop foundations and techniques for next generation big data analytics. The main challenge of existing approaches is the lack of reliability and trustworthiness: if experts do not trust a model or its predictions they are much less likely to use and rely on that model. Hence, we focused on solutions to bring the human-in-the-loop, enabling the diagnostics and refinement of models, and support in decision making and justification. This chapter zooms in on the part of the project focused on developing explainable and trustworthy machine learning techniques.

KW - Visualization

KW - Visual Analytics

KW - Machine Learning

KW - Interpretability

KW - Explainability

KW - XAI

KW - Explain-ability

UR - https://www.scopus.com/pages/publications/85208933403

U2 - 10.4230/OASIcs.Commit2Data.8

DO - 10.4230/OASIcs.Commit2Data.8

M3 - Chapter

T3 - OpenAccess Series in Informatics (OASIcs)

SP - 8:1-8:11

BT - Commit2Data

A2 - Haverkort, Boudewijn R.

A2 - de Jongste, Aldert

A2 - van Kuilenburg, Pieter

A2 - Vromans, Ruben D.

PB - Schloss Dagstuhl - Leibniz-Zentrum für Informatik

ER -

RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance

Abstract

Publication series

Funding

Keywords

Access to Document

Other files and links

Fingerprint

RATE Analytics: Human-in-the-loop

Cite this

RATE-Analytics: Next Generation Predictive Analytics for Data-Driven Banking and Insurance

Abstract

Publication series

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Press/Media

RATE Analytics: Human-in-the-loop

Cite this