TensorRec vs spotlight

Python recommender-system frameworks compared

tensorrec and spotlight are Python projects for building recommendation systems. tensorrec centers on customizable representations and losses with TensorFlow, while spotlight offers factorization and sequence-model building blocks with PyTorch.

TensorRecspotlight
LanguagePythonPython
LicenseApache-2.0MIT
Stars1.3k3k
Forks219416
Last analyzedOct 16, 2026Oct 8, 2026

Key differences

  • tensorrec uses TensorFlow and lets developers customize user and item representations and loss functions; spotlight is built around PyTorch and includes factorization and sequence models.
  • tensorrec supports ranked recommendations from user features, item features, and interaction data; spotlight covers explicit rating prediction, implicit-feedback ranking, and next-item recommendations.
  • tensorrec includes recall-at-k evaluation and dummy-data generation; spotlight includes dataset utilities, train/test splitting, and recommendation evaluation.
  • tensorrec uses the Apache-2.0 license; spotlight uses the MIT license.
  • tensorrec states that it is no longer under active development, with no further planned updates expected; spotlight was last pushed on 2022-12-21, so compatibility should be checked before adoption.

Choose TensorRec if you…

  • need TensorFlow-based recommender workflows using user features, item features, and interaction data.
  • want to customize model representations and loss functions.
  • prefer a project that includes recall-at-k evaluation and dummy-data generation.
Read the TensorRec analysis →

Choose spotlight if you…

  • need building blocks for explicit-rating, implicit-ranking, or sequential recommendation experiments.
  • want to compare factorization models, ranking losses, or sequence architectures with PyTorch.
  • prefer included MovieLens and synthetic-data utilities, along with train/test splitting.
Read the spotlight analysis →

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.