nach oben

2024 | Buch

Kapitel lesen Erstes Kapitel lesen

Insurance, Biases, Discrimination and Fairness

verfasst von: Arthur Charpentier

Verlag: Springer Nature Switzerland

Buchreihe : Springer Actuarial

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book offers an introduction to the technical foundations of discrimination and equity issues in insurance models, catering to undergraduates, postgraduates, and practitioners. It is a self-contained resource, accessible to those with a basic understanding of probability and statistics. Designed as both a reference guide and a means to develop fairer models, the book acknowledges the complexity and ambiguity surrounding the question of discrimination in insurance. In insurance, proposing differentiated premiums that accurately reflect policyholders' true risk—termed "actuarial fairness" or "legitimate discrimination"—is economically and ethically motivated. However, such segmentation can appear discriminatory from a legal perspective. By intertwining real-life examples with academic models, the book incorporates diverse perspectives from philosophy, social sciences, economics, mathematics, and computer science. Although discrimination has long been a subject of inquiry in economics and philosophy, it has gained renewed prominence in the context of "big data," with an abundance of proxy variables capturing sensitive attributes, and "artificial intelligence" or specifically "machine learning" techniques, which often involve less interpretable black box algorithms.

The book distinguishes between models and data to enhance our comprehension of why a model may appear unfair. It reminds us that while a model may not be inherently good or bad, it is never neutral and often represents a formalization of a world seen through potentially biased data. Furthermore, the book equips actuaries with technical tools to quantify and mitigate potential discrimination, featuring dedicated chapters that delve into these methods.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

Although the algorithms of machine-learning methods have brought issues of discrimination and fairness back to the forefront, these topics have been the subject of an extensive body of literature over the past decades. But dealing with discrimination in insurance is fundamentally an ill-defined, unsolvable problem. Nevertheless, we try to connect the dots, to explain different perspectives, going back to the legal, philosophical, and economic approaches to discrimination, before discussing the so-called concept of “actuarial fairness.” We offer some definitions, an overview of the book, as well as the datasets used in the illustrative examples throughout the chapters.

Arthur Charpentier

Insurance and Predictive Modeling

Frontmatter

Chapter 2. Fundamentals of Actuarial Pricing

Abstract

“Insurance is the contribution of the few to the misfortune of the many” is a simple way to describe what insurance is. But it doesn’t say what the “contribution” should be, to be fair. In this chapter, we return to the fundamentals of pricing and risk sharing, and at the end we mention other models used in insurance (to predict future payments to be provisioned, to create a fraud score, etc.).

Arthur Charpentier

Chapter 3. Models: Overview on Predictive Models

Abstract

In this chapter, we give an overview on predictive modeling, used by actuaries. Historically, we moved from relatively homogeneous portfolios to tariff classes, and then to modern insurance, with the concept of “premium personalization.” Modern modeling techniques are presented, starting with econometric approaches, before presenting machine-learning techniques.

Arthur Charpentier

Chapter 4. Models: Interpretability, Accuracy, and Calibration

Abstract

In this chapter, we present important concepts for when dealing with predictive models. We start with a discussion about the interpretability and explainability of models and algorithms, presenting different tools that could help us to understand “why” the predicted outcome of the model is the one we got. Then, we will discuss accuracy, which is usually the ultimate target of most machine-learning techniques. But as we see, the most important concept is the “good calibration” of the model, which means that we want to have, locally, a balanced portfolio, and that the probability predicted by the model is, indeed, related to the true risk.

Arthur Charpentier

Data

Frontmatter

Chapter 5. What Data?

Abstract

Actuaries now collect all kinds of information about policyholders, which can not only be used to refine a premium calculation but also to carry out prevention operations. We return here to the choice of relevant variables in pricing, with emphasis on actuarial, operational, legal and ethical motivations. In particular, we discuss the idea of capturing information on the behavior of an insured person, and the difficult reconciliation with the strong constraints not only of privacy but also of fairness.

Arthur Charpentier

Chapter 6. Some Examples of Discrimination

Abstract

We return here to the usual protected, or sensitive, variables that can lead to discrimination in insurance. We mention direct discrimination, with race and ethnic origin, gender and sex, or age. We also discuss genetic-related discrimination, and as several official protected attributes are not related to biology but to social identity, we return to this concept. We also discuss other inputs used by insurers, that could be related to sensitive attributes, with text, pictures, and spatial information, and could be seen as some discrimination by proxy. We also mention the use of credit scores and network data.

Arthur Charpentier

Chapter 7. Observations or Experiments: Data in Insurance

Abstract

An important challenge for actuaries is that they need to answer causal questions with observational data. After a brief discussion about correlation and causality, we describe the “causation ladder,” and the three rungs: association or correlation (“what if I see...”), intervention (“what if I do...”), and counterfactuals (“what if I had done...”). Counterfactuals are important for quantifying discrimination.

Arthur Charpentier

Fairness

Frontmatter

Chapter 8. Group Fairness

Abstract

Assessing whether a model is discriminatory, or not, is a complex problem. As in Chap. 3, where we discussed global and local interpretability of predictive models, we start with some global approaches (the local ones will be discussed in Chap. 9), also called “group fairness,” comparing quantities between groups, usually identified by sensitive attributes (e.g., gender, ethnicity, age, etc.). Using the formalism introduced in the previous chapters, y denotes the variable of interest, \(\widehat {y}\) or \(m(\boldsymbol {x})\) denotes the prediction given by the model, and s the sensitive attribute. Most concepts are derived from three main principles: independence (

https://static-content.springer.com/image/chp%3A10.1007%2F978-3-031-49783-4_8/601740_1_En_8_IEq3_HTML.gif

ModifyingAbove y With caret perpendicular perpendicular s

), separation (

https://static-content.springer.com/image/chp%3A10.1007%2F978-3-031-49783-4_8/601740_1_En_8_IEq4_HTML.gif

ModifyingAbove y With caret perpendicular perpendicular s

conditional on y), and sufficiency ((

https://static-content.springer.com/image/chp%3A10.1007%2F978-3-031-49783-4_8/601740_1_En_8_IEq5_HTML.gif

y perpendicular perpendicular s

) conditional on \(\widehat {y}\)). We review these approaches here, linking them while opposing them, and we implement metrics related to those notions on various datasets.

Arthur Charpentier

Chapter 9. Individual Fairness

Abstract

Group fairness, as studied in Chap. 8, considered fairness from a global perspective, in the entire population, by attempting to answer the question “are individuals in the advantaged group and in the disadvantaged group treated differently?” Or more formally, are the predictions and the protected variable globally independent? Here, we focus on a specific individual, in the disadvantaged group, and we talk about discrimination (in a broad sense, or inequity) by asking what the model would have predicted if this same person had been in the favored group. We return here to the classical approaches, emphasizing the different approaches to constructing a counterfactual for this individual.

Arthur Charpentier

Mitigation

Frontmatter

Chapter 10. Pre-processing

Abstract

“Pre-processing” is about distorting the training sample to ensure that the model we obtain is “fair,” with respect to some criteria (defined in the previous chapters). The two standard techniques are either to modify the original dataset (and to distort features to make them “fair,” or independent of the sensitive attribute), or to use weights (as used in surveys to correct for biases). If there are poor theoretical guarantees, there are also legal issues with those techniques.

Arthur Charpentier

Chapter 11. In-processing

Abstract

Classically, to estimate a model, we look for a model (in a pre-defined class) that minimizes a prediction error, or that maximizes the accuracy. If the model is required to satisfy constraints, a natural idea is to add a penalty term in the objective function. The idea of “in-processing” is to get a trade-off between accuracy and fairness. As previously, we present that approach to some datasets.

Arthur Charpentier

Chapter 12. Post-Processing

Abstract

The idea of “post-processing” is relatively simple, as we change neither the training data, nor the model that has been estimated; we simply transform the predictions obtained, to make them “fair” (according to some specific criteria). As actuaries care about calibration, and the associated concept of a “well-balanced” model, quite naturally, we use averages and barycenters. Using optimal transport, we describe techniques, with strong mathematical guarantees, that could be used to get a “fair” pricing model.

Arthur Charpentier

Backmatter

Titel: Insurance, Biases, Discrimination and Fairness
verfasst von: Arthur Charpentier
Verlag: Springer Nature Switzerland
Electronic ISBN: 978-3-031-49783-4
Print ISBN: 978-3-031-49782-7
DOI: https://doi.org/10.1007/978-3-031-49783-4