Mallows model is a model that is often exploited for analyzing ranking data.
In Bayesian framework, we can take advantage of posterior samples obtained from MCMC to analyze rank data.
Probabilistic preference learning with the Mallows rank model by V.Vitelli introduced the Bayesian Mallows rank model and the Metropolis-Hastings algorithm for obtaining MCMC samples.
Since the method can be extended to partial ranking or pairwise comparison, we can also apply it to the individual recommendation.