fastFM vs TensorRec
Python recommendation and factorization machine projects compared
fastFM provides scikit-learn-style factorization machine estimators for regression, classification, and ranking. tensorrec is a TensorFlow framework focused on building recommendation systems from user features, item features, and interaction data, with customizable representations and loss functions.

fastFM: Factorization Machines for Python
fastFM brings factorization machines to Python through a scikit-learn-style API, with C and Cython implementations of solvers for regression, classification, and ranking. It suits machine-learning practitioners who need factorization models, but the repository has been inactive for years.

TensorRec: Build Recommendation Systems with TensorFlow
TensorRec is a Python recommendation framework built on TensorFlow. It lets developers customize recommendation and ranking algorithms using user features, item features, and interaction data.
| fastFM | TensorRec | |
|---|---|---|
| Language | Python | Python |
| License | — | Apache-2.0 |
| Stars | 1.1k | 1.3k |
| Forks | 203 | 219 |
| Last analyzed | Oct 15, 2026 | Oct 16, 2026 |
Key differences
- fastFM focuses on factorization machines across regression, classification, and ranking, while tensorrec focuses on recommendation workflows and ranked item suggestions.
- fastFM offers SGD, coordinate descent, and MCMC solvers; tensorrec supports customization of representation and embedding functions and loss functions through TensorFlow.
- fastFM combines a Python API with performance-critical C code wrapped through Cython; tensorrec is built around TensorFlow-based model customization.
- fastFM reports its license as NOASSERTION, while tensorrec reports Apache-2.0. fastFM's README says BSD, so verify its applicable license before use.
- tensorrec says it is no longer under active development and expects no further planned updates. fastFM's listed considerations flag compatibility checks because its last push was on 2022-07-17.
- fastFM's README identifies Linux and OS X as tested platforms and says other operating systems are not actively supported; tensorrec's stated workflow uses TensorFlow.
Choose fastFM if you…
- need factorization machines for regression, classification, or ranking.
- want to compare SGD, coordinate descent, and MCMC optimization options.
- work with sparse feature data and want scikit-learn-style estimators.
Choose TensorRec if you…
- want to build recommendation models from user features, item features, and interaction data.
- need customizable representations and loss functions in a TensorFlow workflow.
- want utilities for ranked recommendations, recall-at-k evaluation, or dummy data generation.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.