Online NMF

Online NMF (Non-negative matrix factorization) is a recently developed method for real time data analysis in an online context. Non-negative matrix factorization in the past has been used for static data analysis and pattern recognition. In the past it has been used for facial recognition and spectral data analysis, however due to the time and memory expensive nature of NMF algorithms2, PCA, SVD, and Pearson correlation based methods have been used instead. However, the fact that data can be recreated as a linear combination of the set of resolved "basis" data is advantageous in some lines of study. One such use is for collaborative filtering in recommendation systems where it is advantageous to know not only how much two individuals are alike, which can be derived from the Pearson correlation, but also in what ways are they alike. The purpose of the online NMF algorithm is to perform rapid NMF analysis so that recommendations can be produced in real time.