« Back to Results

Advances in Big Data Research in Economics

Paper Session

Saturday, Jan. 6, 2018 2:30 PM - 4:30 PM

Marriott Philadelphia Downtown, Liberty Ballroom Salon A
Hosted By: American Economic Association
  • Chair: Fatih Guvenen, University of Minnesota

Origins of Wealth Inequality

Andreas Fagereng
Statistics Norway
Luigi Guiso
Einaudi Institute for Economics and Finance
Fatih Guvenen
University of Minnesota
Joachim Hubmer
Yale University
Luigi Pistaferri
Stanford University


This paper uses a 20-year panel on the population of Norwegian households to identify the determinants of wealth accumulation. The data set includes detailed information on portfolio composition of households, including their ownership in private businesses, and allows us to compute the rate of return earned by each household in each year. We combining this information with a rich set of demographics, income data, labor supply, and other variables that interact with savings decision, and apply machine learning tools in the context of a structural economic model to detect key patterns in wealth accumulation. In particular, we are interested in decomposing the wealth holdings of households in different percentiles of the wealth distribution into components coming from precautionary savings motive, retirement savings, non-homothetic preferences, differences in rates of return, and differences in patience.

Labor Market Equilibration: Evidence from Uber

Jonathan V. Hall
Uber Technologies
John Horton
New York University
Dan Knoepfle
Uber Technologies


Using a city-week panel of US ride-sharing markets created by Uber,
we estimate the effects of sudden fare changes on market outcomes, focusing
on the supply-side. We explore both the short-run dynamics of
market adjustment, as well as the eventual long-run equilibrium. We
find that the driver hourly earnings rate—essentially the market equilibrium
wage—moves immediately in the same direction as a fare change,
but that these effects are short-lived. The prevailing wage returns to its
pre-change level within about 8 weeks. This return is achieved primarily
through permanent changes in driver “utilization,” or the fraction of
hours-worked that are spent transporting passengers. Our results imply
that the driver supply of labor to ride-sharing markets is highly elastic,
most likely because drivers face no quantity restrictions on how many
hours to supply and new drivers face minimal barriers to entry.

Human Decisions and Machine Predictions

Jon Kleinberg
Cornell University
Himabindu Himabindu Lakkaraju
Stanford University
Jure Leskovec
Stanford University
Jens Ludwig
University of Chicago
Sendhil Mullainathan
Harvard University


We examine how machine learning can be used to improve and understand human decision-making. In particular, we focus on a decision that has important policy consequences. Millions of times each year, judges must decide where defendants will await trial—at home or in jail. By law, this decision hinges on the judge’s prediction of what the defendant would do if released. This is a promising machine learning application because it is a concrete prediction task for which there is a large volume of data available. Yet comparing the algorithm to the judge proves complicated. First, the data are themselves generated by prior judge decisions. Second, judges may have a broader set of preferences than the single variable that the algorithm focuses on; for instance, judges may care about racial inequities or about specific crimes (such as violent crimes) rather than just overall crime risk. Even accounting for these concerns, our results suggest potentially large welfare gains: a policy simulation shows crime can be reduced by up to 24.8% with no change in jailing rates, or jail populations can be reduced by 42.0% with no increase in crime rates. Moreover, we see reductions in all categories of crime, including violent ones.
JEL Classifications
  • J0 - General
  • E2 - Consumption, Saving, Production, Investment, Labor Markets, and Informal Economy