If the data is non-negative, Non-negative Matrix Factorization can be used to cluster the observations, the variables, or both. By its nature, NMF clustering is focused on the large values. Our idea is to normalize the data, e.g. by subtracting the row/column means, and split the matrix into positive and negative parts. NMF clustering applied to the concatenated data, “PosNegNMF”, gives equal weight to large and small values. The approach along with powerful visualizations tools is available in JMP through our platform: inferential & robust Matrix Factorization, irMF. A light automated demo is included with the slides.