An Economic Approach to Regulating Algorithms

@article{Rambachan2020AnEA,
  title={An Economic Approach to Regulating Algorithms},
  author={Ashesh Rambachan and Jon M. Kleinberg and Sendhil Mullainathan and Jens Ludwig},
  journal={NBER Working Paper Series},
  year={2020}
}
There is growing concern about "algorithmic bias" - that predictive algorithms used in decision-making might bake in or exacerbate discrimination in society. When will these "biases" arise? What should be done about them? We argue that such questions are naturally answered using the tools of welfare economics: a social welfare function for the policymaker, a private objective function for the algorithm designer and a model of their information sets and interaction. We build such a model that… 
Unpacking the Black Box: Regulating Algorithmic Decisions
TLDR
It is shown that limiting agents to prediction functions that are simple enough to be fully transparent is inefficient as long as the bias induced by misalignment between principal's and agent’s preferences is small relative to the uncertainty about the true state of the world.
Algorithmic Design: Fairness Versus Accuracy
TLDR
A model in which a designer chooses an algorithm that maps observed inputs into decisions is proposed, and simple statistical properties of the algorithm’s inputs that determine the shape of the accuracy-fairness Pareto frontier are identified.
MACHINE LEARNING FOR STRATEGIC INFERENCE
TLDR
It is shown how Adaptive Boosting algorithms can be specified to induce behavior that is (approximately) as-if rational using only observed data, and in particular without needing to infer the optimal response from Bayes rule.
Fair Decisions Despite Imperfect Predictions
TLDR
The results suggest the need for a paradigm shift in the context of fair machine learning from the currently prevalent idea of simply building predictive models from a single static dataset via risk minimization, to a more interactive notion of "learning to decide".
Fairness constraint in Structural Econometrics and Application to fair estimation using Instrumental Variables
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
Identifying Prediction Mistakes in Observational Data*
Decision makers, such as doctors, judges, and managers, make consequential choices based on predictions of unknown outcomes. Do these decision makers make systematic prediction mistakes based on the
Protecting the Protected Group: Circumventing Harmful Fairness
TLDR
The welfare-Equalizing approach provides a unified framework for discussing fairness in classification in the presence of a self-interested party and finds that the disadvantaged protected group can be worse off after imposing a fairness constraint.
Constrained Classification and Policy Learning
TLDR
Conditions on the constrained set of classifiers that can guarantee consistency of hinge risk minimizing classifiers are characterized, showing that in settings where the constraint restricts the classifier’s prediction set only, hinge losses are the only surrogate losses that preserve consistency in second-best scenarios.
Resolving the Disparate Impact of Uncertainty: Affirmative Action vs. Affirmative Information
TLDR
It is shown that predictive uncertainty often leads classifiers to systematically disadvantage groups with lower-mean outcomes, assigning them smaller true and false positive rates than their higher-mean counterparts, and it is proved that to avoid these error imbalances, individuals in lower- Mean groups must either be over-represented among positive classifications or be assigned more accurate predictions.
Hiring as Exploration
TLDR
This paper builds a resume screening algorithm that values exploration by evaluating candidates according to their statistical upside potential, and shows that this approach improves the quality and increases demographic diversity, relative to the firm's existing practices.
...
1
2
3
...

References

SHOWING 1-10 OF 48 REFERENCES
Algorithmic Decision Making and the Cost of Fairness
TLDR
This work reformulate algorithmic fairness as constrained optimization: the objective is to maximize public safety while satisfying formal fairness constraints designed to reduce racial disparities, and also to human decision makers carrying out structured decision rules.
Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making
TLDR
This work provides both heuristic justification and empirical evidence suggesting that a lower-bound on the welfare-based measures often leads to bounded inequality in algorithmic outcomes; hence presenting the first computationally feasible mechanism for bounding individual-level inequality.
Fair classification and social welfare
TLDR
This paper presents a welfare-based analysis of fair classification regimes and shows that applying stricter fairness criteria codified as parity constraints can worsen welfare outcomes for both groups.
Discrimination in the Age of Algorithms
TLDR
Algorithms are not only a threat to be regulated; with the right safeguards in place, they have the potential to be a positive force for equity.
Fairness-aware Learning through Regularization Approach
TLDR
This paper discusses three causes of unfairness in machine learning and proposes a regularization approach that is applicable to any prediction algorithm with probabilistic discriminative models and applies it to logistic regression to empirically show its effectiveness and efficiency.
Certifying and Removing Disparate Impact
TLDR
This work links disparate impact to a measure of classification accuracy that while known, has received relatively little attention and proposes a test for disparate impact based on how well the protected class can be predicted from the other attributes.
Algorithmic Social Engineering
TLDR
This article applies classic strategic communication models to the microeconomics of using algorithms to nudge decision-makers toward particular social outcomes, and emphasizes separating preferences and predictions in designing algorithmic interventions.
Welfare and Distributional Impacts of Fair Classification
TLDR
A new framework for interpreting the effects of fairness criteria is proposed by converting the constrained loss minimization problem into a social welfare maximization problem that moves a classifier and its output into utility space where individuals, groups, and society at-large experience different welfare changes due to classification assignments.
Fairness-Aware Classifier with Prejudice Remover Regularizer
TLDR
A regularization approach is proposed that is applicable to any prediction algorithm with probabilistic discriminative models and applied to logistic regression and empirically show its effectiveness and efficiency.
The Allocation of Decision Authority to Human and Artificial Intelligence
The allocation of decision authority by a principal to either a human agent or an artificial intelligence (AI) is examined. The principal trades off an AI’s more aligned choice with the need to
...
1
2
3
4
5
...