Andrew Blair Hillis

Photo of Andrew Blair Hillis

Contact:

Send Email

Doctoral Student

Andrew Hillis a PhD candidate at the Harvard Economics Department and Harvard Business School. His research uses machine learning, field experiments, and insights from behavioral economics to study productivity and innovation, particularly in healthcare. 
 
His research has been published in the American Economic Review: Papers & Proceedings and the Harvard Business Review. One project has examined the productivity gains associated with data-driven hiring for teachers and police officers. Another explores the use of open tournaments in city government to source algorithms for targeting hygiene inspection violations from public data. He has collaborated with Yelp and the City of Boston and is passionate about working with organizations to produce relevant and rigorous research.

Publications

Journal Articles

  1. Productivity and Selection of Human Capital with Machine Learning

    Aaron Chalfin, Oren Danieli, Andrew Hillis, Zubin Jelveh, Michael Luca, Jens Ludwig and Sendhil Mullainathan

    Keywords: Data and Data Sets; Selection and Staffing; Performance Productivity; Mathematical Methods; Policy;

    Citation:

    Chalfin, Aaron, Oren Danieli, Andrew Hillis, Zubin Jelveh, Michael Luca, Jens Ludwig, and Sendhil Mullainathan. "Productivity and Selection of Human Capital with Machine Learning."American Economic Review: Papers and Proceedings 106, no. 5 (May 2016): 124–127. View Details
  2. Crowdsourcing City Government: Using Tournaments to Improve Inspection Accuracy

    Edward Glaeser, Andrew Hillis, Scott Duke Kominers and Michael Luca

    The proliferation of big data makes it possible to better target city services like hygiene inspections, but city governments rarely have the in-house talent needed for developing prediction algorithms. Cities could hire consultants, but a cheaper alternative is to crowdsource competence by making data public and offering a reward for the best algorithm. A simple model suggests that open tournaments dominate consulting contracts when cities can tolerate risk and when there is enough labor with low opportunity costs. We also report on an inexpensive Boston-based restaurant tournament, which yielded algorithms that proved reasonably accurate when tested "out-of-sample" on hygiene inspections.

    Keywords: user-generated content; operations; tournaments; policy-making; Machine learning; online platforms; Data and Data Sets; Mathematical Methods; City; Infrastructure; Business Processes; Government and Politics;

    Citation:

    Glaeser, Edward, Andrew Hillis, Scott Duke Kominers, and Michael Luca. "Crowdsourcing City Government: Using Tournaments to Improve Inspection Accuracy."American Economic Review: Papers and Proceedings 106, no. 5 (May 2016): 114–118. View Details
        17 Oct 2016
        Harvard Business Review

        Area of Study

        • Negotiation, Organizations and Markets