The evaluation of the performance of mutual funds (MFs) has been a very interesting research topic not only for researchers, but also for managers of financial, banking and investment institutions. This paper explores the performance of a non-parametric approach in developing MF performance evaluation models. The proposed approach is based on the UTADIS multicriteria decision aid method. The data set consists of daily data for 33 Greek domestic equity MFs, and is used to estimate the performance of the method in classifying the funds into two groups. A cross-validation procedure is employed to evaluate the predictive performance of the models and a comparison with linear discriminant analysis is also performed. The results indicate the superiority of the UTADIS method as opposed to the traditional discrimination technique.
