Towards Explainability of Machine Learning Models in Insurance Pricing

03/24/2020 ∙ by Kevin Kuo, et al. ∙ 0 ∙ share

Machine learning methods have garnered increasing interest among actuaries in recent years. However, their adoption by practitioners has been limited, partly due to the lack of transparency of these methods, as compared to generalized linear models. In this paper, we discuss the need for model interpretability in property casualty insurance ratemaking, propose a framework for explaining models, and present a case study to illustrate the framework.

READ FULL TEXT VIEW PDF

POST COMMENT

Comments

There are no comments yet.

Authors

Kevin Kuo
6 publications
Daniel Lupton
1 publication

page 1

page 2

page 3

page 4

InterpretML: A Unified Framework for Machine Learning Interpretability

InterpretML is an open-source Python package which exposes machine learn...
09/19/2019 ∙ by Harsha Nori, et al. ∙ 0 ∙ share

read it
Addressing the interpretability problem for deep learning using many valued quantum logic

Deep learning models are widely used for various industrial and scientif...
07/02/2020 ∙ by Swapnil Nitin Shah, et al. ∙ 0 ∙ share

read it
A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers

Our research aims to propose a new performance-explainability analytical...
05/29/2020 ∙ by Kevin Fauvel, et al. ∙ 0 ∙ share

read it
Machine Learning for Public Administration Research, with Application to Organizational Reputation

Machine learning methods have gained a great deal of popularity in recen...
05/11/2018 ∙ by L. Jason Anastasopoulos, et al. ∙ 0 ∙ share

read it
Assessing the Local Interpretability of Machine Learning Models

The increasing adoption of machine learning tools has led to calls for a...
02/09/2019 ∙ by Sorelle A. Friedler, et al. ∙ 0 ∙ share

read it
Reconciled Polynomial Machine: A Unified Representation of Shallow and Deep Learning Models

In this paper, we aim at introducing a new machine learning model, namel...
05/19/2018 ∙ by Jiawei Zhang, et al. ∙ 0 ∙ share

read it
Utilizing a Transparency-driven Environment toward Trusted Automatic Genre Classification: A Case Study in Journalism History

With the growing abundance of unlabeled data in real-world tasks, resear...
10/01/2018 ∙ by Aysenur Bilgin, et al. ∙ 0 ∙ share

read it

Towards Explainability of Machine Learning Models in Insurance Pricing

Authors

InterpretML: A Unified Framework for Machine Learning Interpretability

Addressing the interpretability problem for deep learning using many valued quantum logic

A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers

Machine Learning for Public Administration Research, with Application to Organizational Reputation

Assessing the Local Interpretability of Machine Learning Models

Reconciled Polynomial Machine: A Unified Representation of Shallow and Deep Learning Models

Utilizing a Transparency-driven Environment toward Trusted Automatic Genre Classification: A Case Study in Journalism History

1 Introduction

2 Property and Casualty Ratemaking

3 The Need to See Inside the Black Box

4 Interpretability in the Ratemaking Context

5 Applying Model Interpretation Techniques

6 Conclusion

Acknowledgments

References

Appendix

Appendix A Model Development

Towards Explainability of Machine Learning Models in Insurance Pricing

Authors

InterpretML: A Unified Framework for Machine Learning Interpretability

Addressing the interpretability problem for deep learning using many valued quantum logic

A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers

Machine Learning for Public Administration Research, with Application to Organizational Reputation

Assessing the Local Interpretability of Machine Learning Models

Reconciled Polynomial Machine: A Unified Representation of Shallow and Deep Learning Models

Utilizing a Transparency-driven Environment toward Trusted Automatic Genre Classification: A Case Study in Journalism History

This week in AI

1 Introduction

2 Property and Casualty Ratemaking

3 The Need to See Inside the Black Box

4 Interpretability in the Ratemaking Context

5 Applying Model Interpretation Techniques

6 Conclusion

Acknowledgments

References

Appendix

Appendix A Model Development