Machine Predictions and Human Decisions with Variation in Payoffs and Skills
Publikation: Working paper › Forskning
Standard
Machine Predictions and Human Decisions with Variation in Payoffs and Skills. / Ribers, Michael Allen; Ullrich, Hannes.
2020.Publikation: Working paper › Forskning
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - UNPB
T1 - Machine Predictions and Human Decisions with Variation in Payoffs and Skills
AU - Ribers, Michael Allen
AU - Ullrich, Hannes
PY - 2020/11/6
Y1 - 2020/11/6
N2 - 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.
AB - 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.
KW - Faculty of Social Sciences
KW - Prediction policy
KW - expert decision-making
KW - machine learning
KW - antibiotic prescribing
UR - https://www.mendeley.com/catalogue/55753175-3635-319f-b043-a7bcd472c713/
U2 - 10.2139/ssrn.3726018
DO - 10.2139/ssrn.3726018
M3 - Working paper
T3 - DIW Berlin Discussion Paper
BT - Machine Predictions and Human Decisions with Variation in Payoffs and Skills
ER -
ID: 251993688