Wei Tan, Research Staff Member at IBM T. J. Watson Research Center shares how IBM is using NVIDIA GPUs to accelerate recommender systems, which use ratings or user behavior to recommend new products, items or content to users. Recommender systems are important in applications such as recommending products on retail sites, recommending movies or music on streaming media services, and recommending news items or posts on social media and networking services. Wei Tan’s team developed cuMF, a highly optimized matrix factorization system using CUDA to accelerate recommendations used in applications like these and more.

**Brad: Can you talk a bit about your current research?**

Wei: Matrix factorization (MF) is at the core of many popular algorithms, such as collaborative-filtering-based recommendation, word embedding, and topic modeling. Matrix factorization factors a sparse ratings matrix (*m*-by-*n*, with non-zero ratings) into a *m*-by-*f* matrix (*X*) and a *f*-by-*n* matrix (Θ^{T}), as Figure 1 shows.

Suppose we obtained *m* users’ ratings on items (say, movies). If user *u* rated item *v*, we use as the non-zero element of *R* at position (*u*, *v*). We want to minimize the following cost function *J*. Continue reading