LocalGLMnet: interpretable deep learning for tabular data

24 Pages Posted: 26 Jul 2021

See all articles by Ronald Richman

Ronald Richman

Old Mutual Insure; University of the Witwatersrand

Mario V. Wuthrich

RiskLab, ETH Zurich

Date Written: July 23, 2021

Abstract

Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep learning models is that their solutions are difficult to interpret and explain, and variable selection is not easily possible because deep learning models solve feature engineering and variable selection internally in a nontransparent way. Inspired by the appealing structure of generalized linear models, we propose a new network architecture that shares similar features as generalized linear models, but provides superior predictive power benefiting from the art of representation learning. This new architecture allows for variable selection of tabular data and for interpretation of the calibrated deep learning model, in fact, our approach provides an additive decomposition in the spirit of Shapley values and integrated gradients.

Keywords: deep learning, neural networks, generalized linear model, regression model, variable selection, explainable deep learning, attention layer, tabular data, exponential dispersion family, Shapley values, SHapley Additive exPlanations (SHAP), integrated gradients

JEL Classification: G22, C45, C12, C31

Suggested Citation

Richman, Ronald and Wuthrich, Mario V., LocalGLMnet: interpretable deep learning for tabular data (July 23, 2021). Available at SSRN: https://ssrn.com/abstract=3892015 or http://dx.doi.org/10.2139/ssrn.3892015

Ronald Richman

Old Mutual Insure ( email )

Wanooka Place
St Andrews Road
Johannesburg, 2192
South Africa

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Mario V. Wuthrich (Contact Author)

RiskLab, ETH Zurich ( email )

Department of Mathematics
Ramistrasse 101
Zurich, 8092
Switzerland

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

Paper statistics

Downloads
123
Abstract Views
513
rank
282,405
PlumX Metrics