matrix-factorization
implicit
| matrix-factorization | implicit | |
|---|---|---|
| 1 | 3 | |
| 19 | 3,427 | |
| - | - | |
| 2.9 | 6.2 | |
| 7 months ago | about 2 months ago | |
| Python | Python | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
matrix-factorization
-
Recently launched my first end-to-end ML app! A film recommender system based on matrix factorization, built for Letterboxd users.
I originally tried using RiverML, which is dedicated to online ML, but after a ton of tweaking I still wasn't satisfied. In the end, I used the matrix-factorization library, which is not at all flashy but worked much, much better. By adjusting the learning rate and epochs for feeding new ratings into the model I can adjust how "personalized" the ratings are, and after a few days of messing with it I got it where I wanted it.
implicit
- Recommendation system integration
-
Content-based Recommender System with Python
Although CF methods also have some explainability available. CF library https://github.com/benfred/implicit which I used a lot in my past projects, e.g. has the method model.explain available for that.
-
Tensorflow Recommender (TFRS) or Scikit-Surprise?
In that case, you are doing some form of collaborative filtering, though you can also add content-based filtering as additional features later. You can use either implicit or explicit feedback. I would suggest checking this package, and this tutorial. Let me know if you have any other questions.
What are some alternatives?
LightFM - A Python implementation of LightFM, a hybrid recommendation algorithm.
fastapi - FastAPI framework, high performance, easy to learn, fast to code, ready for production
annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
riscv-newop - A RISC-V new instruction discovery tool [Work in Progress]
fastFM - fastFM: A Library for Factorization Machines
spotlight - Deep recommender models using PyTorch.
TensorRec - A TensorFlow recommendation algorithm and framework in Python.
LT-OCF - LT-OCF: Learnable-Time ODE-based Collaborative Filtering, CIKM'21
RecBole - A unified, comprehensive and efficient recommendation library
libffm - A Library for Field-aware Factorization Machines