Risk-aversion in data envelopment analysis models with diversification

We deal with data envelopment analysis models with diversification which can identify investment op-portunities efficient with respect to several inputs and outputs represented by risk and return measures. Moreover, they enable to project the inefficient investment opportunity to the efficient frontier and sug-gest how to revise its structure. However, the current DEA models does not take into account the individ-ual risk aversion of a particular investor. We will introduce several approaches based on the spectral risk measures which deal with this drawback. These approaches are then compared in the empirical study. Note that all considered models as well as risk aversion are consistent with the second order stochastic dominance. (c) 2020 Elsevier Ltd. All rights reserved.

Automated summary

The study focuses on data envelopment analysis models that can identify efficient investment opportunities, but do not consider the individual risk aversion of investors. Several approaches based on spectral risk measures are introduced to address this drawback, and are compared in an empirical study.