TY - JOUR
T1 - Case-based decision theory
AU - Gilboa, Itzhak
AU - Schmeidler, David
N1 - Funding Information:
influenced this work. In particular, we benefited from insightful conversations with Eva Gilboa, who also exposed us to case-based reasoning, and Akihiko Matsui and Kimberly Katz, who also referred us to Hume. A special thank-you is due to Benjamin Polak who served as a referee. His two reports on earlier versions of the paper are longer than the final product. His suggestions reshaped the paper and made it much more accessible to a reader who is not one of the authors. We are also grateful to the faculty and students of the Institute for the Learning Sciences at Northwestern University, faculty and guests at the Santa Fe Institute, as well as to Max Bazerman, Avraham Beja, Edward Green, Ehud Kalai, Morton Kamien, Edi Karni, Simon Kasif, James Peck, Stanley Reiter, Ariel Rubinstein, Michael Sang, Karl Schlag, Andrei Shleifer, Costis Skiadas, Steven Tadelis, and Amos Tversky for comments and references. Partial financial support from NSF Grants Nos. SES-9113108 and SES-9111873, the Alfred Sloan Foundation, and the Suntory Foundation are gratefully acknowledged.
PY - 1995/8
Y1 - 1995/8
N2 - This paper suggests that decision-making under uncertainty is, at least partly, case-based. We propose a model in which cases are primitive, and provide a simple axiomatization of a decision rule that chooses a “best” act based on its past performance in similar cases. Each act is evaluated bythe sum of the utility levels that resulted from using this act in past cases, each weighted by the similarity of that past case to the problem at hand. The formal model of case-based decision theory naturally gives rise to the notions of satisficing decisions and aspiration levels.
AB - This paper suggests that decision-making under uncertainty is, at least partly, case-based. We propose a model in which cases are primitive, and provide a simple axiomatization of a decision rule that chooses a “best” act based on its past performance in similar cases. Each act is evaluated bythe sum of the utility levels that resulted from using this act in past cases, each weighted by the similarity of that past case to the problem at hand. The formal model of case-based decision theory naturally gives rise to the notions of satisficing decisions and aspiration levels.
UR - http://www.scopus.com/inward/record.url?scp=77952373089&partnerID=8YFLogxK
U2 - 10.2307/2946694
DO - 10.2307/2946694
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:77952373089
SN - 0033-5533
VL - 110
SP - 605
EP - 639
JO - Quarterly Journal of Economics
JF - Quarterly Journal of Economics
IS - 3
ER -