Shapley Lorenz Values for Artificial Intelligence Risk Management

20 Pages Posted: 9 Mar 2021

See all articles by Niklas Bussmann

Niklas Bussmann

affiliation not provided to SSRN

Roman Enzmann

affiliation not provided to SSRN

Paolo Giudici

University of Pavia

Emanuela Raffinetti

University of Pavia

Date Written: March 8, 2021

Abstract

A trustworthy application of Artificial Intelligence requires to measure in advance its possible risks. When applied to regulated industries, such as banking, finance and insurance, Artificial Intelligence methods lack explainability and, therefore, authorities aimed at monitoring risks may not validate them. To solve this issue, explainable machine learning methods have been introduced to "interpret" black box models. Among them, Shapley values are becoming popular: they are model agnostic, and easy to interpret. However, they are not normalised and, therefore, cannot become a standard procedure for Artificial Intelligence risk management. This paper proposes an alternative explainable machine learning method, based on Lorenz Zonoids, that is statistically normalised, and can therefore be used as a standard for the application of Artificial Intelligence.

The empirical analysis of 15,000 small and medium companies asking for credit confirms the advantages of our proposed method.

Keywords: Artificial Intelligence, Lorenz Zonoids, Shapley values, Risk management

JEL Classification: C18, C51, C52, C71

Suggested Citation

Bussmann, Niklas and Enzmann, Roman and Giudici, Paolo and Raffinetti, Emanuela, Shapley Lorenz Values for Artificial Intelligence Risk Management (March 8, 2021). Available at SSRN: https://ssrn.com/abstract=3800243 or http://dx.doi.org/10.2139/ssrn.3800243

Niklas Bussmann

affiliation not provided to SSRN

Roman Enzmann

affiliation not provided to SSRN

Paolo Giudici

University of Pavia ( email )

Via San Felice 7
27100 Pavia, 27100
Italy

Emanuela Raffinetti (Contact Author)

University of Pavia ( email )

Via San Felice 5
Pavia, 27100
Italy

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
238
Abstract Views
796
Rank
246,739
PlumX Metrics