A new choice paradigm available to academic and applied choice modelers is Random Regret Minimization (RRM). RRM works from the assumption that what drives choice is the avoidance of regret: a chooser selects the alternative that minimizes her chance for regretting her decision. The authors (Keith Chrzan and Jefferson Forkner) introduce RRM and discuss some of its interesting properties. They describe how to analyze RRM models in standard logit and HB software packages like Sawtooth Software's Latent Class and CBC/HB. The results of two marketing research applications conducted to compare RRM and standard CBC in terms of predictive validity find that the two perform about equally well. The authors also discuss the relative strengths and weaknesses of RRM.