Table 4 Mean absolute error (MAE) measurements for the four subgroups and four personalized recommendation algorithms. NMF (in bold) outperforms all other algorithms for all subgroups. Among the subgroups, the best accuracy results (i.e., lowest MAE scores) are reached by \(U_{\text{ambi}}\), while the worst accuracy results (i.e., highest MAE scores) are reached by \(U_{\text{hard}}\). To facilitate comparison, we also show the MAE measurements for the BeyMS and MS user groups

From: Support the underground: characteristics of beyond-mainstream music listeners