A new model of random regret minimization

Abstract

A new choice model is derived, rooted in the framework of Random Regret inimization(RRM). The proposed model postulates that when choosing, people anticipate and aim to minimize regret. Whereas previous regret-based discrete choice-models assume that regret is experienced with respect to only the best of foregone alternatives, the proposed model assumes that regret is potentially experienced with respect to each foregone alternative that performs well. In contrast with earlier regret-based discrete-choice approaches, this model can be estimated using readily available discrete-choice software packages. The proposed model is contrasted theoretically and empirically with its natural counterpart, Random Utility Maximization's linear- additive MNL-model. Empirical comparisons on four revealed and stated travel choice datasets show a promising performance of the RRM-model.