RECORD
Fairness constraint in Structural Econometrics and Application to fair estimation using Instrumental Variables
Econometrics · Submitted 16 Feb 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Achieving \textit{approximate fairness} is obtained by introducing a fairness penalty in the learning procedure and balancing more or less heavily the influence between the status quo and a full fair solution.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
A supervised machine learning algorithm determines a model from a learning sample that will be used to predict new observations. To this end, it aggregates individual characteristics of the observations of the learning sample. But this information aggregation does not consider any potential selection on unobservables and any status-quo biases which may be contained in the training sample. The latter bias has raised concerns around the so-called \textit{fairness} of machine learning algorithms, especially towards disadvantaged groups. In this chapter, we review the issue of fairness in machine learning through the lenses of structural econometrics models in which the unknown index is the solution of a functional equation and issues of endogeneity are explicitly accounted for. We model fairness as a linear operator whose null space contains the set of strictly {\it fair} indexes. A {\it fair} solution is obtained by projecting the unconstrained index into the null space of this operator or by directly finding the closest solution of the functional equation into this null space. We also acknowledge that policymakers may incur a cost when moving away from the status quo. Achieving \textit{approximate fairness} is obtained by introducing a fairness penalty in the learning procedure and balancing more or less heavily the influence between the status quo and a full fair solution.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | A supervised machine learning algorithm determines a model from a learning sample that will be used to predict new observations. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | To this end, it aggregates individual characteristics of the observations of the learning sample. | background 0.96 | 0.06 | 0.02 | asserted 1.00 |
| s2 | But this information aggregation does not consider any potential selection on unobservables and any status-quo biases which may be contained in the training sample. | background 0.56 | 0.06 | 0.03 | asserted 0.83 |
| s3 | The latter bias has raised concerns around the so-called \textit{fairness} of machine learning algorithms, especially towards disadvantaged groups. | background 1.00 | 0.05 | 0.03 | asserted 0.90 |
| s4 | In this chapter, we review the issue of fairness in machine learning through the lenses of structural econometrics models in which the unknown index is the solution of a functional equation and issues of endogeneity are explicitly accounted for. | contribution 0.95 | 0.30 | 0.09 | asserted 0.88 |
| s5 | We model fairness as a linear operator whose null space contains the set of strictly {\it fair} indexes. | method 0.86 | 0.73 | 0.12 | asserted 1.00 |
| s6 | A {\it fair} solution is obtained by projecting the unconstrained index into the null space of this operator or by directly finding the closest solution of the functional equation into this null space. | method 0.97 | 0.58 | 0.24 | asserted 1.00 |
| s7 | We also acknowledge that policymakers may incur a cost when moving away from the status quo. | background 0.66 | 0.09 | 0.04 | hedged possibility 0.96 |
| s8 | Achieving \textit{approximate fairness} is obtained by introducing a fairness penalty in the learning procedure and balancing more or less heavily the influence between the status quo and a full fair solution. | method 0.87 | 0.47 | 0.20 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
A supervised machine learning algorithm determines a model from a learning sample that will be used to predict new observations. To this end, it aggregates individual characteristics of the observations of the learning sample. But this information aggregation does not consider any potential selection on unobservables and any status-quo biases which may be contained in the training sample. The latter bias has raised concerns around the so-called \textit{fairness} of machine learning algorithms, especially towards disadvantaged groups. In this chapter, we review the issue of fairness in machine learning through the lenses of structural econometrics models in which the unknown index is the solution of a functional equation and issues of endogeneity are explicitly accounted for. We model fairness as a linear operator whose null space contains the set of strictly {\it fair} indexes. A {\it fair} solution is obtained by projecting the unconstrained index into the null space of this operator or by directly finding the closest solution of the functional equation into this null space. We also acknowledge that policymakers may incur a cost when moving away from the status quo. Achieving \textit{approximate fairness} is obtained by introducing a fairness penalty in the learning procedure and balancing more or less heavily the influence between the status quo and a full fair solution.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.