ML FOR ECONOMIC POLICY

FRIDAY DECEMBER 11, NEURIPS 2020
  • Can machine learning be used to help with the development of effective economic policy?
  • Can we understand economic behavior through granular, economic data sets?
  • Can we automate economic transactions for individuals?
  • How can we build rich and faithful simulations of economic systems with strategic agents?

Machine learning offers enormous potential to transform our understanding of economics, economic decision making, and public policy. Yet its adoption by economists, social scientists, and policymakers remains nascent.

This workshop will highlight both the opportunities as well as the barriers to the adoption of ML in economics. In particular, we aim to accelerate the use of machine learning to rapidly develop, test, and deploy effective economic policies that are grounded in representative data.

This workshop will expose some of the critical socio-economic issues that stand to benefit from applying machine learning, expose underexplored economic datasets and simulations, and identify machine learning research directions that would have a significant positive socio-economic impact. This includes policies and mechanisms that target socio-economic issues such as diversity and fair representation in economic outcomes, economic equality, and improving economic opportunity.

Introduction

Michael Kearns

Best Paper (Empirical)

Doina Precup

Panel Discussion: Algorithms & Methodology

Susan Athey

Best Paper (Methodology)

Sendhil Mullainathan

Panel Discussion: ML in Economics & Real-World Policy

ACCEPTED PAPERS

A Scalable Inference Method For Large Dynamic Economic Systems
Pratha Khandelwal, Philip Nadler, Rossella Arcucci, William Knottenbelt and Yi-Ke Guo
PDF

Kernel Methods for Policy Evaluation: Treatment Effects, Mediation Analysis, and Off-Policy Planning
Rahul Singh, Liyuan Xu and Arthur Gretton
PDF

Counterfactual Demand Predictions: Deep Learning with Microeconomic Theory
Dong Soo Kim, Chul Kim, Mingyu Joo and Hai Che
PDF

Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling
Naveen Raman, Sanket Shah and John Dickerson
PDF

Deep learning for understanding economic well-being in Africa from publicly available satellite imagery
Christopher Yeh, Anthony Perez, Anne Driscoll, George Azzari, Zhongyi Tang, David Lobell, Stefano Ermon and Marshall Burke
PDF

Where does the Stimulus go? Deep Learning for Commercial Banking Deposits
Ni Zhan
PDF

Regulating algorithmic filtering on social media
Sarah Cen and Devavrat Shah
PDF

Incentivizing Bandit Exploration: Recommendations as Instruments
Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis and Zhiwei Steven Wu
PDF

Pandemic Response as Reinforcement Learning
Blake Elias, Alex Siegenfeld and Yaneer Bar-Yam
PDF

(Machine) Learning what Policymakers Value
Daniel Bjorkegren, Joshua Blumenstock and Samsun Knight
PDF

BEST EMPIRICAL PAPER AWARD
Estimating Policy Functions in Payment Systems using Reinforcement Learning
Ajit Desai, Han Du, Francisco Rivadeneyra, Rodney Garratt and Pablo S Castro
PDF

Mostly Harmless Machine Learning: Learning Optimal Instruments in Linear IV Models
Jiafeng Chen, Daniel Chen and Greg Lewis
PDF

Dynamic Pricing with Bayesian Updates from Online Reviews
Andrew Xia, Jose Correa and Mathieu Mari
PDF

A Multiagent Model of Efficient and Sustainable Financial Markets
Betty Shea, Mark Schmidt and Maryam Kamgarpour
PDF

Fairness Under Partial Compliance
Jessica Dai, Sina Fazelpour and Zachary Lipton
PDF

Learning and utility in multi-agent congestion control
Pratiksha Thaker, Tatsunori Hashimoto and Matei Zaharia
PDF

Reinforcement Learning of Simple Indirect Mechanisms
Gianluca Brero, Alon Eden, Matthias Gerstgrasser, David C. Parkes and Duncan Rheingans-Yoo
PDF

Bandit Data-driven Optimization: AI for Social Good and Beyond
Zheyuan Ryan Shi, Zhiwei Steven Wu, Rayid Ghani and Fei Fang
PDF

Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
Shengjia Zhao and Stefano Ermon
PDF

BEST METHODOLOGY PAPER AWARD
Empirical Welfare Maximization with Constraints
Liyang Sun
PDF

Certifying Strategyproof Auction Networks
Michael Curry, Ping-Yeh Chiang, Tom Goldstein and John P. Dickerson
PDF

ORGANIZATION

Nika Haghtalab

Cornell

Annie Liang

UPenn

Jamie Morgenstern

UW

David C. Parkes

Harvard

Alex Trott

Salesforce

Stephan Zheng

Salesforce

PROGRAM COMMITTEE

Alexander Trott, Salesforce Research

Annie Liang, University of Pennsylvania

Bhuvesh Kumar, Georgia Institute of Technology

Bo Waggoner, U. Colorado

Chara Podimata, Harvard University

David Parkes, Harvard University

Ellen Vitercik, Carnegie Mellon University

Eric Sodomka, Facebook

Gianluca Brero, Harvard University

Hadi Elzayn, University of Pennsylvania

James Wright, University of Alberta

Jamie Morgenstern, University of Washington

Jann Spiess, Stanford Graduate School of Business

Kevin Lai, Georgia Institute of Technology

Matthias Gerstgrasser, University of Oxford

Nika Haghtalab, Microsoft Research / Cornell

Nikhil Naik, Salesforce

Stephan Zheng, Salesforce

Sunil Srinivasa, Salesforce Research

Zachary Schutzman, University of Pennsylvania