# FHIM Factorized sparse learning models with interpretable high order feature interactions #Attention This repository implements the FHIM model proposed in KDD14. However, this is not official code provided by author. The efficiency is potential to be improved. I have tested such code on synthetic data and I suppose it is identical to performacne reported in paper. However, I will not be responsible for consequence of result of this code. #Class The FHIM class implements the function of algorithms. It supports both the numpy array input or scipy.sparse.csr_matrix input. The support for high order interaction, or tensor, is not finished. And I do not think I will add this function in near future.