The Disparate Effects of Strategic Manipulation

By Lily Hu, Nicole Immorlica, Jennifer Wortman Vaughan. 2018

182 citations recorded by the source corpus.

When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system's approval. Models of agent responsiveness, termed "strategic manipulation," analyze the interaction between a learner and agents in a world where all agents are equally able to manipulate their features in an attempt to "trick" a published classifier. In cases of real world classification, however, an agent's ability to adapt to an algorithm is not simply a function of her personal interest in receiving a positive classification, but is bound up in a complex web of social factors that affect her ability to pursue certain action responses. In this paper, we adapt models of strategic manipulation to capture dynamics that may arise in a setting of social inequality wherein candidate groups face different costs to manipulation. We find that whenever one group's costs are higher than the other's, the learner's equilibrium strategy exhibits an inequality-reinforcing phenomenon wherein the learner erroneously admits some members of the advantaged group, while erroneously excluding some members of the disadvantaged group. We also consider the effects of interventions in which a learner subsidizes members of the disadvantaged group, lowering their costs in order to improve her own classification performance. Here we encounter a paradoxical result: there exist cases in which providing a subsidy improves only the learner's utility while actually making both candidate groups worse-off---even the group receiving the subsidy. Our results reveal the potentially adverse social ramifications of deploying tools that attempt to evaluate an individual's "quality" when agents' capacities to adaptively respond differ.

Subfields: Management Science and Operations Research, Safety Research, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Safety Research

In Statistical and Nonlinear Physics

Citations in the corpus

Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “While it may be possible to make predictions robust to strategic behavior, this may also have social costs, especially for disadvantaged groups [79, 121].”
Actionable Recourse in Linear Classification (2018, background): “These include: inverse classification, which aims to determine how the inputs to a model can be manipulated to obtain a desired outcome [1, 10]; strategic classification, which considers how to build classifiers that are robust to malicious manipulation [13, 16, 21, 22, 30]; adversarial perturbation”
Explainable AI: A Review of Machine Learning Interpretability Methods (2020, background): “In [82] strategic manipulation models were studied and adapted in an environment of social inequality, in which different social groups have to pay different costs of manipulation.”
How Do Classifiers Induce Agents to Invest Effort Strategically? (2018, background): “in the case of spam detection, and more recently in terms of Stackelberg competitions, in which the evaluator publishes a rule and the agent may respond by manipulating their features strategically [5, 13, 18, 23, 29].”
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach (2020, background): “Fairness in dynamical systems has been explored in speciﬁc domains: predictive policing (Lum & Isaac, 2016; Ensign et al., 2018), hiring (Hu & Chen, 2018; Hu et al., 2019), lending (Mouzannar et al., 2019), and RSs (Chaney et al., 2018; Bountouridis et al., 2019).”
The Social Cost of Strategic Classification (2018, background): “[18] also study negative externalities of strategic classification.”
Optimal Decision Making Under Strategic Behavior (2019, background): “ are incentivized to use this knowledge to invest effort strategically in order to receive a beneﬁcial decision. With this motivation, there has been a recent ﬂurry of work on strategic classiﬁcation [1, 2, 5, 6, 8, 11, 16]. This line of work has focused on the development of accurate predictive mod”
Economics, Fairness and Algorithmic Bias (2020, unknown): “Hu et al. (2018) formally modeled screening games in which some agents have a cost advantage for manipulating.”
Fairness in Machine Learning: A Survey (2020, unknown): “[187, 92, 94, 135, 204]).”
The philosophical basis of algorithmic recourse (2020, background): “The second aspect draws a contrast with other literature that considers the problem of strategic manipulation of features to achieve a desired goal[14, 16, 24].”
Performative Prediction (2020, background): “Recent work in this area considers issues of incentive design [23, 27], control over an algorithm [7], and fairness concerns [17, 28].”
This Thing Called Fairness (2019, background): “Notably, strategic behavior may have disparate effects (as individuals may have disparate access to the instruments of manipulation) [68] or broader social losses [102].”