Ronald Richman

insureAI

30 Melrose Blvd

Melrose Arch

Johannesburg, Gauteng 2192

South Africa

University of the Witwatersrand

SCHOLARLY PAPERS

30

DOWNLOADS
Rank 2,650

SSRN RANKINGS

Top 2,650

in Total Papers Downloads

26,507

TOTAL CITATIONS
Rank 17,533

SSRN RANKINGS

Top 17,533

in Total Papers Citations

134

Scholarly Papers (30)

Actions:
Email selected abstracts
1.

AI in Actuarial Science

Number of pages: 53 Posted: 15 Aug 2018 Last Revised: 20 Aug 2018
Ronald Richman
insureAI
Downloads 5,356 (3,582)
Citation 9

Abstract:

Loading...

Actuarial Science, Deep Learning, Machine Learning, Insurance, Telematics

2.

AI Tools for Actuaries

Number of pages: 288 Posted: 02 May 2025 Last Revised: 09 May 2025
Mario V. Wuthrich, Ronald Richman, Benjamin Avanzi, Mathias Lindholm, Michael Mayer, Jürg Schelldorfer and Salvatore Scognamiglio
RiskLab, ETH Zurich, insureAI, University of Melbourne - Centre for Actuarial Studies, Stockholm University, Schweizerische Mobiliar Versicherungsgesellschaft, Swiss Re and University of Naples "Parthenope"
Downloads 4,705 (4,507)

Abstract:

Loading...

3.

The Actuary and IBNR Techniques: A Machine Learning Approach

Number of pages: 53 Posted: 11 Nov 2020 Last Revised: 13 Nov 2020
Caesar Balona and Ronald Richman
Old Mutual Insure and insureAI
Downloads 3,176 (8,488)
Citation 3

Abstract:

Loading...

IBNR, machine learning, reserving, short-term insurance, non-life insurance

4.

Lee and Carter go Machine Learning: Recurrent Neural Networks

Number of pages: 30 Posted: 23 Aug 2019 Last Revised: 29 Aug 2019
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich
Downloads 2,112 (16,251)
Citation 23

Abstract:

Loading...

recurrent neural network (RNN), long short-term memory (LSTM), gated recurrent unit (GRU), Lee-Carter (LC) model, mortality forecasting, feed-forward neural network (FNN)

5.

A Neural Network Extension of the Lee-Carter Model to Multiple Populations

Number of pages: 21 Posted: 01 Nov 2018 Last Revised: 07 Nov 2018
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich
Downloads 1,563 (26,012)
Citation 36

Abstract:

Loading...

Mortality forecasting, Lee-Carter model, Multiple Populations, Neural Networks

6.

Neural Network Embedding of the Over-Dispersed Poisson Reserving Model

Number of pages: 30 Posted: 14 Dec 2018
Andrea Gabrielli, Ronald Richman and Mario V. Wuthrich
ETH Zurich, Department of Mathematics, RiskLab, Students, insureAI and RiskLab, ETH Zurich
Downloads 1,248 (36,217)
Citation 10

Abstract:

Loading...

cross-classified over-dispersed Poisson model, neural network, model blending, nested models, learning across portfolios, claims reserving in insurance, chain-ladder reserves, mean square error of prediction

7.

Time-Series Forecasting of Mortality Rates using Deep Learning

Number of pages: 26 Posted: 04 Jun 2020
Francesca Perla, Ronald Richman, Salvatore Scognamiglio and Mario V. Wuthrich
University of Naples Parthenope - Department of Management Studies and Quantitative Methods, insureAI, University of Naples "Parthenope" and RiskLab, ETH Zurich
Downloads 1,213 (37,717)
Citation 17

Abstract:

Loading...

Mortality Forecasting, Recurrent Neural Networks, Convolutional Neural Networks, Representation Learning, Time-Series Forecasting, Lee Carter Model, Human Mortality Database

8.

Mind the Gap - Safely Incorporating Deep Learning Models into the Actuarial Toolkit

Number of pages: 63 Posted: 03 Jun 2021
Ronald Richman
insureAI
Downloads 687 (82,572)
Citation 1

Abstract:

Loading...

Deep learning, actuarial science

9.

Believing the Bot - Model Risk in the Era of Deep Learning

Number of pages: 40 Posted: 05 Sep 2019
Ronald Richman, Nicolai von Rummell and Mario V. Wuthrich
insureAI, QED Actuaries and Consultants and RiskLab, ETH Zurich
Downloads 653 (88,079)
Citation 13

Abstract:

Loading...

Deep learning, Model Risk, Pricing, Mortality Forecasting, Insurance Modelling

10.

Reflections on deep learning and the actuarial profession(al)

Number of pages: 28 Posted: 17 Jan 2024
Roseanne Harris, Ronald Richman and Mario V. Wuthrich
University of Witwatersrand, Johannesburg, South Africa, insureAI and RiskLab, ETH Zurich
Downloads 651 (88,447)

Abstract:

Loading...

11.

An AI Vision for the Actuarial Profession

Number of pages: 11 Posted: 19 Mar 2024
Ronald Richman
insureAI
Downloads 554 (108,582)

Abstract:

Loading...

Artificial Intelligence, Deep Learning, Actuarial Profession, AI-Enhanced Actuary, Insurance, Risk Management, Explainable AI, Discrimination-Free Pricing

12.

What is fair? Proxy discrimination vs. demographic disparities in insurance pricing

Number of pages: 37 Posted: 14 May 2023 Last Revised: 05 Jul 2024
Mathias Lindholm, Ronald Richman, Andreas Tsanakas and Mario V. Wuthrich
Stockholm University, insureAI, Bayes Business School (formerly Cass), City, University of London and RiskLab, ETH Zurich
Downloads 538 (112,725)
Citation 7

Abstract:

Loading...

discrimination, indirect discrimination, proxy discrimination, fairness, protected attributes, discrimination-free, unawareness, group fairness, demographic parity, statistical parity, independence axiom, equalized odds, separation axiom, predictive parity, sufficiency axiom, input pre-process

13.

Using Machine Learning to Model Claims Experience and Reporting Delays for Pricing and Reserving

Number of pages: 44 Posted: 16 Oct 2019
Louis Rossouw and Ronald Richman
Gen Re - South Africa and insureAI
Downloads 504 (122,075)

Abstract:

Loading...

machine learning, IBNR, experience analysis, reinsurers

14.

Smoothness and Monotonicity Constraints for Neural Networks Using ICEnet

Number of pages: 33 Posted: 21 May 2023
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich
Downloads 502 (122,656)
Citation 2

Abstract:

Loading...

Smoothing, Whittaker–Henderson Smoothing, Graduation, Monotonicity, Deep Neural Networks, Constrained Likelihood, Individual Conditional Expectation

15.

LASSO Regularization within the LocalGLMnet Architecture

Number of pages: 29 Posted: 24 Sep 2021 Last Revised: 01 Jun 2022
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich
Downloads 456 (137,793)
Citation 3

Abstract:

Loading...

Deep learning, neural networks, LocalGLMnet, regression model, variable selection, regularization, LASSO, group LASSO, ridge regularization, Tikhonov regularization.

16.

A Discussion of Discrimination and Fairness in Insurance Pricing

Number of pages: 14 Posted: 18 Sep 2022
Mathias Lindholm, Ronald Richman, Andreas Tsanakas and Mario V. Wuthrich
Stockholm University, insureAI, Bayes Business School (formerly Cass), City, University of London and RiskLab, ETH Zurich
Downloads 412 (155,033)

Abstract:

Loading...

discrimination, indirect discrimination, proxy discrimination, fairness, protected information, discrimination-free, unawareness, group fairness, statistical parity, independence axiom, equalized odds, separation axiom, predictive parity, sufficiency axiom

17.

A Multi-Task Network Approach for Calculating Discrimination-Free Insurance Prices

Number of pages: 33 Posted: 19 Jul 2022 Last Revised: 02 Nov 2022
Mathias Lindholm, Ronald Richman, Andreas Tsanakas and Mario V. Wuthrich
Stockholm University, insureAI, Bayes Business School (formerly Cass), City, University of London and RiskLab, ETH Zurich
Downloads 399 (160,741)
Citation 8

Abstract:

Loading...

indirect discrimination, proxy discrimination, discrimination-free insurance pricing, unawareness price, best-estimate price, protected information, discriminatory covariates, fairness, incomplete information, multi-task learning, multioutput network

18.

Accurate and Explainable Mortality Forecasting with the LocalGLMnet

Number of pages: 27 Posted: 10 Mar 2023
Francesca Perla, Ronald Richman, Salvatore Scognamiglio and Mario V. Wuthrich
University of Naples Parthenope - Department of Management Studies and Quantitative Methods, insureAI, University of Naples "Parthenope" and RiskLab, ETH Zurich
Downloads 386 (166,812)

Abstract:

Loading...

Mortality forecasting, explainable deep learning, neural networks, Lee–Carter model, multi-population mortality model, Human Mortality Database, LocalGLMnet

19.

Applying Deep Learning in Actuarial Science

Number of pages: 322 Posted: 08 Mar 2024
Ronald Richman
insureAI
Downloads 371 (174,419)
Citation 1

Abstract:

Loading...

20.

Conditional Expectation Network for SHAP

Number of pages: 24 Posted: 25 Jul 2023
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich
Downloads 267 (247,912)
Citation 1

Abstract:

Loading...

Shapley value, SHAP, conditional SHAP, unconditional SHAP, interventional SHAP, anova, drop1, analysis-of-deviance, least squares Monte Carlo, partial dependence plot, PDP, explainability, XAI

21.

Sensitivity-Based Measures of Discrimination in Insurance Pricing

Number of pages: 34 Posted: 19 Aug 2024 Last Revised: 23 Dec 2024
Mathias Lindholm, Ronald Richman, Andreas Tsanakas and Mario V. Wuthrich
Stockholm University, insureAI, Bayes Business School (formerly Cass), City, University of London and RiskLab, ETH Zurich
Downloads 219 (301,530)

Abstract:

Loading...

Proxy discrimination, demographic parity, insurance pricing, algorithmic fairness, sensitivity analysis

22.

Mortality Improvements in South Africa: Insights from Pensioner Mortality

Number of pages: 46 Posted: 28 Oct 2020
Ronald Richman and Gary Velcich
insureAI and Alexander Forbes Financial Services (Pty) Ltd
Downloads 202 (325,519)

Abstract:

Loading...

Mortality, Lee Carter model, Neural Networks, Deep Learning, IFRS 17, Uncertainty quantification

23.

Why the HAF Is Not the Head of the Actuarial Function?

Number of pages: 45 Posted: 18 Nov 2020
Mike Ilsley, Ronald Richman, Nicolai von Rummell and Edmond Vigoureux
Professional Independent Director, insureAI, QED Actuaries and Consultants and QED Actuaries and Consultants
Downloads 177 (367,282)

Abstract:

Loading...

Head of Actuarial Function, Actuarial Function

24.

Is LASSO Credibility Credible?

Number of pages: 27 Posted: 15 Jan 2025
Ronald Richman
insureAI
Downloads 156 (410,044)

Abstract:

Loading...

Actuarial Science, Credibility Theory, LASSO, LASSO Credibility, ASOP 25

25.

High-Cardinality Categorical Covariates in Network Regressions

Japenese Journal of Statistics and Data Science. Open Access: https://link.springer.com/article/10.1007/s42081-024-00243-4
Posted: 24 Aug 2023 Last Revised: 13 Mar 2024
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich

Abstract:

Loading...

categorical covariates, categorical features, nominal features, high-cardinality features, entity embedding, embedding layer, random effects model, neural network, re- current neural network, attention layer, transformer, regularization, ridge regularization, variational inference

26.

LocalGLMnet: interpretable deep learning for tabular data

Scandinavian Actuarial Journal 2022 https://www.tandfonline.com/doi/full/10.1080/03461238.2022.2081816
Posted: 26 Jul 2021 Last Revised: 09 Jun 2022
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich

Abstract:

Loading...

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

27.

Interpreting Deep Learning Models with Marginal Attribution by Conditioning on Quantiles

Data Mining and Knowledge Discovery (2022) https://link.springer.com/article/10.1007/s10618-022-00841-4
Posted: 22 Mar 2021 Last Revised: 22 Jun 2022
Michael Merz, Ronald Richman, Andreas Tsanakas and Mario V. Wuthrich
University of Hamburg, insureAI, Bayes Business School (formerly Cass), City, University of London and RiskLab, ETH Zurich

Abstract:

Loading...

explainable AI (XAI), model-agnostic tools, deep learning, attribution, accumulated local e ects (ALE), partial dependence plot (PDP), locally interpretable model-agnostic explanation (LIME), variable importance, post-hoc analysis

28.

Nagging Predictors

Risks 2020, 8(3), 83; https://doi.org/10.3390/risks8030083
Posted: 16 Jul 2020 Last Revised: 22 Mar 2021
Ronald Richman and Mario V. Wuthrich
insureAI and RiskLab, ETH Zurich

Abstract:

Loading...

bagging, neural networks, network aggregation, insurance pricing, regression modeling

29.

Discrimination-Free Insurance Pricing

ASTIN Bulletin open access FirstView 2021 https://www.cambridge.org/core/journals/astin-bulletin-journal-of-the-iaa/article/discriminationfree-insurance-pricing/ED25C4053690E56050F437B8DF2AD117
Posted: 10 Feb 2020 Last Revised: 11 Oct 2021
Mathias Lindholm, Ronald Richman, Andreas Tsanakas and Mario V. Wuthrich
Stockholm University, insureAI, Bayes Business School (formerly Cass), City, University of London and RiskLab, ETH Zurich

Abstract:

Loading...

discrimination, differentiation, insurance pricing, individual policy char- acteristics, discriminatory covariates, direct discrimination, indirect discrimination, neural networks, complex algorithmic models, causal inference, confounding

30.

Mortality Improvements -- The Case of South Africa

Posted: 02 Aug 2014 Last Revised: 28 Oct 2014
Ronald Richman and Matthew Simmons
insureAI and University of the Witwatersrand

Abstract:

Loading...

Mortality Improvement, South Africa, Stochastic modeling