In this study we propose a Deep structured LOw Rank Matrix Approximation model (DLORMA) that incorporates additional stacked denoising autoencoders and local matrix approximations in a loosely coupled fashion. To the best of our knowledge, DLORMA is the first hybrid recommendation system that combines deep learning and low rank matrix approximation. Comprehend experiments based on three real datasets show improvements in prediction performance over other state-of-the-art recommendation systems.