skip to main content

Title: Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic policies which explicitly trade off between a private objective (such as profit) and a public objective (such as social welfare). We analyze a natural class of policies which trace an empirical Pareto frontier based on learned scores, and focus on how such decisions can be made in noisy or data-limited regimes. Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimal strategies and a rich class of fairness-constrained profit-maximizing policies. We then present empirical results in two different contexts — online content recommendation and sustainable abalone fisheries — to underscore the generality of our approach to a wide range of practical decisions. Taken together, these results shed light on inherent trade-offs in using machine learning for decisions that impact social welfare.
Authors:
; ; ; ; ; ;
Award ID(s):
1942702
Publication Date:
NSF-PAR ID:
10218811
Journal Name:
Proceedings of Machine Learning Research
Volume:
119
Page Range or eLocation-ID:
8158-8168
ISSN:
2640-3498
Sponsoring Org:
National Science Foundation
More Like this
  1. While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic policies which explicitly trade off between a private objective (such as profit) and a public objective (such as social welfare). We analyze a natural class of policies which trace an empirical Pareto frontier based on learned scores, and focus on how such decisions can be made in noisy or data-limited regimes. Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimalmore »strategies and a rich class of fairness-constrained profit-maximizing policies. We then present empirical results in two different contexts — online content recommendation and sustainable abalone fisheries — to underscore the generality of our approach to a wide range of practical decisions. Taken together, these results shed light on inherent trade-offs in using machine learning for decisions that impact social welfare.« less
  2. The emergence of the sharing economy in urban transportation networks has enabled new fast, convenient and accessible mobility services referred to as Mobilty-on-Demand systems (e.g., Uber, Lyft, DiDi). These platforms have flourished in the last decade around the globe and face many operational challenges in order to be competitive and provide good quality of service. A crucial step in the effective operation of these systems is to reduce customers' waiting time while properly selecting the optimal fleet size and pricing policy. In this paper, we jointly tackle three operational decisions: (i) fleet size, (ii) pricing, and (iii) rebalancing, in ordermore »to maximize the platform's profit or its customers' welfare. To accomplish this, we first devise an optimization framework which gives rise to a static policy. Then, we elaborate and propose dynamic policies that are more responsive to perturbations such as unexpected increases in demand. We test this framework in a simulation environment using three case studies and leveraging traffic flow and taxi data from Eastern Massachusetts, New York City, and Chicago. Our results show that solving the problem jointly could increase profits between 1% and up to 50%, depending on the benchmark. Moreover, we observe that the proposed fleet size yield utilization of the vehicles in the fleet is around 75% compared to private vehicle utilization of 5%.« less
  3. A significant body of research in the data sciences considers unfair discrimination against social categories such as race or gender that could occur or be amplified as a result of algorithmic decisions. Simultaneously, real-world disparities continue to exist, even before algorithmic decisions are made. In this work, we draw on insights from the social sciences brought into the realm of causal modeling and constrained optimization, and develop a novel algorithmic framework for tackling pre-existing real-world disparities. The purpose of our framework, which we call the “impact remediation framework,” is to measure real-world disparities and discover the optimal intervention policies thatmore »could help improve equity or access to opportunity for those who are underserved with respect to an outcome of interest. We develop a disaggregated approach to tackling pre-existing disparities that relaxes the typical set of assumptions required for the use of social categories in structural causal models. Our approach flexibly incorporates counterfactuals and is compatible with various ontological assumptions about the nature of social categories. We demonstrate impact remediation with a hypothetical case study and compare our disaggregated approach to an existing state-of-the-art approach, comparing its structure and resulting policy recommendations. In contrast to most work on optimal policy learning, we explore disparity reduction itself as an objective, explicitly focusing the power of algorithms on reducing inequality.« less
  4. Abstract

    Background. Though many studies have long considered the broad social implications of climate change, researchers have only recently started to consider the gendered unevenness of the global landscape of vulnerability, exposure, and adaptive capacity to environmental stressors and shocks. Historically, policies and interventions addressing natural resource-based livelihoods have rarely considered underlying gender dynamics despite the global pervasiveness of gendered disparities in both economic opportunities and welfare outcomes.Methods/Design. Using two electronic databases, Web of Science and Scopus, we conducted a systematic review of peer-reviewed academic literature describing livelihoods policies or interventions that included documentation of gendered impacts. We focused onmore »natural resource-based livelihoods most likely to be affected by climate change, centering on interventions targeting agriculture, fisheries and aquaculture, and forestry.Review Results/Synthesis. We identified 131 relevant articles, most of which focus on adoption or participation in interventions rather than outcomes. In general, women are less likely than men to engage with sustainable livelihoods interventions. When women do engage, some researchers have documented income and food security gains as well as improvements in environmental indicators in the short-term. However, these initiatives have also been found to increase women’s labor burden without corresponding gains in income. Few studies measure longer-term effects of women’s engagement on welfare and environmental outcomes, a key gap in the literature. Additionally, relatively few studies explore the intersectional impacts of initiatives, such as the added burdens of ethnicity, class, education, or other differences that modify gender disparities.Discussion. Climate change has gendered impacts on natural resource-based livelihoods. In general, existing initiatives designed to increase livelihood resilience fail to reduce gender disparities and improve women’s livelihoods. Greater attention should be paid to gender when designing sustainable livelihoods policies and interventions in order to increase adoption and participation, negotiate trade-offs, improve environmental conditions, and promote broadly beneficial welfare outcomes.

    « less
  5. We present an agent-based model of manipulating prices in financial markets through spoofing: submitting spurious orders to mislead traders who learn from the order book. Our model captures a complex market environment for a single security, whose common value is given by a dynamic fundamental time series. Agents trade through a limit-order book, based on their private values and noisy observations of the fundamental. We consider background agents following two types of trading strategies: the non-spoofable zero intelligence (ZI) that ignores the order book and the manipulable heuristic belief learning (HBL) that exploits the order book to predict price outcomes.more »We conduct empirical game-theoretic analysis upon simulated agent payoffs across parametrically different environments and measure the effect of spoofing on market performance in approximate strategic equilibria. We demonstrate that HBL traders can benefit price discovery and social welfare, but their existence in equilibrium renders a market vulnerable to manipulation: simple spoofing strategies can effectively mislead traders, distort prices and reduce total surplus. Based on this model, we propose to mitigate spoofing from two aspects: (1) mechanism design to disincentivize manipulation; and (2) trading strategy variations to improve the robustness of learning from market information. We evaluate the proposed approaches, taking into account potential strategic responses of agents, and characterize the conditions under which these approaches may deter manipulation and benefit market welfare. Our model provides a way to quantify the effect of spoofing on trading behavior and market efficiency, and thus it can help to evaluate the effectiveness of various market designs and trading strategies in mitigating an important form of market manipulation.« less