Machine Predictions and Human Decisions with Variation in Payoffs and Skill

46 Pages Posted: 24 Nov 2020

See all articles by Michael A. Ribers

Michael A. Ribers

University of Copenhagen

Hannes Ullrich

German Institute for Economic Research (DIW Berlin) - Innovation, Management, Service; University of Copenhagen - Department of Economics

Date Written: 2020

Abstract

Human decision-making differs due to variation in both incentives and available information. This generates substantial challenges for the evaluation of whether and how machine learning predictions can improve decision outcomes. We propose a framework that incorporates machine learning on large-scale administrative data into a choice model featuring heterogeneity in decision maker payoff functions and predictive skill. We apply our framework to the major health policy problem of improving the efficiency in antibiotic prescribing in primary care, one of the leading causes of antibiotic resistance. Our analysis reveals large variation in physicians’ skill to diagnose bacterial infections and in how physicians trade off the externality inherent in antibiotic use against its curative benefit. Counterfactual policy simulations show the combination of machine learning predictions with physician diagnostic skill achieves a 25.4 percent reduction in prescribing and the largest welfare gains compared to alternative policies for estimated as well as plausible hypothetical weights on the antibiotic resistance externality.

JEL Classification: C100, C550, I110, I180, Q280

Suggested Citation

Ribers, Michael Allen and Ullrich, Hannes and Ullrich, Hannes, Machine Predictions and Human Decisions with Variation in Payoffs and Skill (2020). CESifo Working Paper No. 8702, Available at SSRN: https://ssrn.com/abstract=3736484 or http://dx.doi.org/10.2139/ssrn.3736484

Michael Allen Ribers (Contact Author)

University of Copenhagen ( email )

Nørregade 10
Copenhagen, København DK-1165
Denmark

Hannes Ullrich

German Institute for Economic Research (DIW Berlin) - Innovation, Management, Service ( email )

Mohrenstraße 58
Berlin, 10117
Germany
+493089789521 (Phone)

University of Copenhagen - Department of Economics ( email )

Øster Farimagsgade 5, Bygn 26
Copenhagen, 1353
Denmark

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
39
Abstract Views
490
PlumX Metrics