Scalable Recommendation with Hierarchical Poisson Factorization

Prem Gopalan Princeton University, Jake Hofman, David Blei Columbia University
Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, PMLR R13:624-633, 2015.

Abstract

We develop hierarchical Poisson matrix factorization (HPF), a novel method for providing users with high quality recommendations based on implicit feedback, such as views, clicks, or purchases. In contrast to existing recommendation models, HPF has a number of desirable properties. First, we show that HPF more accurately captures the long-tailed user activity found in most consumption data by explicitly considering the fact that users have finite attention budgets. This leads to better estimates of users’ latent preferences, and therefore superior recommendations, compared to competing methods. Second, HPF learns these latent factors by only explicitly considering positive examples, eliminating the often costly step of generating artificial negative examples when fitting to implicit data. Third, HPF is more than just one method—it is the simplest in a class of probabilistic models with these properties, and can easily be extended to include more complex structure and assumptions. We develop a variational algorithm for approximate posterior inference for HPF that scales up to large data sets, and we demonstrate its performance on a wide variety of real-world recommendation problems—users rating movies, listening to songs, reading scientific papers, and reading news articles. Our study reveals that hierarchical Poisson factorization definitively outperforms previous methods, including nonnegative matrix factorization, topic models, and probabilistic matrix factorization techniques.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR13-university15n, title = {Scalable Recommendation with Hierarchical {P}oisson Factorization}, author = {University, Prem Gopalan Princeton and Hofman, Jake and University, David Blei Columbia}, booktitle = {Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence}, pages = {624--633}, year = {2015}, editor = {Meila, Marina and Heskes, Tom}, volume = {R13}, series = {Proceedings of Machine Learning Research}, month = {12--16 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r13/main/assets/university15n/university15n.pdf}, url = {https://proceedings.mlr.press/r13/university15n.html}, abstract = {We develop hierarchical Poisson matrix factorization (HPF), a novel method for providing users with high quality recommendations based on implicit feedback, such as views, clicks, or purchases. In contrast to existing recommendation models, HPF has a number of desirable properties. First, we show that HPF more accurately captures the long-tailed user activity found in most consumption data by explicitly considering the fact that users have finite attention budgets. This leads to better estimates of users’ latent preferences, and therefore superior recommendations, compared to competing methods. Second, HPF learns these latent factors by only explicitly considering positive examples, eliminating the often costly step of generating artificial negative examples when fitting to implicit data. Third, HPF is more than just one method—it is the simplest in a class of probabilistic models with these properties, and can easily be extended to include more complex structure and assumptions. We develop a variational algorithm for approximate posterior inference for HPF that scales up to large data sets, and we demonstrate its performance on a wide variety of real-world recommendation problems—users rating movies, listening to songs, reading scientific papers, and reading news articles. Our study reveals that hierarchical Poisson factorization definitively outperforms previous methods, including nonnegative matrix factorization, topic models, and probabilistic matrix factorization techniques.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Scalable Recommendation with Hierarchical Poisson Factorization %A Prem Gopalan Princeton University %A Jake Hofman %A David Blei Columbia University %B Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2015 %E Marina Meila %E Tom Heskes %F pmlr-vR13-university15n %I PMLR %P 624--633 %U https://proceedings.mlr.press/r13/university15n.html %V R13 %X We develop hierarchical Poisson matrix factorization (HPF), a novel method for providing users with high quality recommendations based on implicit feedback, such as views, clicks, or purchases. In contrast to existing recommendation models, HPF has a number of desirable properties. First, we show that HPF more accurately captures the long-tailed user activity found in most consumption data by explicitly considering the fact that users have finite attention budgets. This leads to better estimates of users’ latent preferences, and therefore superior recommendations, compared to competing methods. Second, HPF learns these latent factors by only explicitly considering positive examples, eliminating the often costly step of generating artificial negative examples when fitting to implicit data. Third, HPF is more than just one method—it is the simplest in a class of probabilistic models with these properties, and can easily be extended to include more complex structure and assumptions. We develop a variational algorithm for approximate posterior inference for HPF that scales up to large data sets, and we demonstrate its performance on a wide variety of real-world recommendation problems—users rating movies, listening to songs, reading scientific papers, and reading news articles. Our study reveals that hierarchical Poisson factorization definitively outperforms previous methods, including nonnegative matrix factorization, topic models, and probabilistic matrix factorization techniques. %Z Reissued by PMLR on 04 October 2026.
APA
University, P.G.P., Hofman, J. & University, D.B.C.. (2015). Scalable Recommendation with Hierarchical Poisson Factorization. Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R13:624-633 Available from https://proceedings.mlr.press/r13/university15n.html. Reissued by PMLR on 04 October 2026.

Related Material