Arbeitspapier
Machine Predictions and Human Decisions with Variation in Payoffs and Skill
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.
- Sprache
-
Englisch
- Erschienen in
-
Series: CESifo Working Paper ; No. 8702
- Klassifikation
-
Wirtschaft
Econometric and Statistical Methods and Methodology: General
Large Data Sets: Modeling and Analysis
Analysis of Health Care Markets
Health: Government Policy; Regulation; Public Health
Renewable Resources and Conservation: Government Policy
- Thema
-
prediction policy
expert decision-making
machine learning
antibiotic prescribing
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Ribers, Michael Allan
Ullrich, Hannes
- Ereignis
-
Veröffentlichung
- (wer)
-
Center for Economic Studies and Ifo Institute (CESifo)
- (wo)
-
Munich
- (wann)
-
2020
- Handle
- Letzte Aktualisierung
-
10.03.2025, 11:42 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Arbeitspapier
Beteiligte
- Ribers, Michael Allan
- Ullrich, Hannes
- Center for Economic Studies and Ifo Institute (CESifo)
Entstanden
- 2020