Zhao, Chen
[VerfasserIn]
;
Ke, Shaowei
[Sonstige Person, Familie und Körperschaft];
Wang, Zhaoran
[Sonstige Person, Familie und Körperschaft];
Hsieh, Sung-Lin
[Sonstige Person, Familie und Körperschaft]
Anmerkungen:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments February 15, 2020 erstellt
Beschreibung:
We provide an axiomatic foundation for a class of neural-network models applied to decision-making under risk, called neural-network expected utility (NEU) models. Motivated by classic experimental findings, we weaken the independence axiom in a novel way. We show how to use simple neurons, referred to as behavioral neurons, in a NEU model to capture behavioral biases such as reference dependence and the certainty effect. Empirically, we find that focusing on NEU models with multiple types of behavioral neurons helps mitigate overfitting, and some simple NEU models with natural interpretation have good predictive power