Statistics and Data Science Seminar: Bayesian non-negative tensor factorization for international trading, by Jie Jian
February 25, 2026
4:15 PM - 5:05 PM
Jie Jian (University of Chicago): Bayesian non-negative tensor factorization for international trading
Detecting dependence structures in international tradesuch as persistent exporterimporter affinities, and supply-chain clusteringoften relies on latent variable models that summarize high-dimensional trading flows. We propose a novel Bayesian non-negative tensor factorization for large, sparse, nonnegative trading tensors with excess zeros and continuous positive measurements. We target settings with millions of entries and extreme sparsity. Each entry follows a spike-and-slab model: a point mass at zero coupled with a gammaPoisson construction that yields a low-rank nonnegative decomposition via gamma latent factors. The framework provides interpretable mode-specific components and principled uncertainty quantification.
Please click here to make changes to, or delete, this seminar announcement.
Date posted
Mar 9, 2026
Date updated
Mar 9, 2026
Speakers
