{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/7"}],"enrichment":{"capability":"Scikit-surprise builds and evaluates recommender systems that predict explicit ratings using algorithms like SVD, matrix factorization, k-NN, and baseline methods.","skillfed_tags":["collaborative-filtering","recommender-systems","machine-learning"],"use_cases":["Evaluate and compare different collaborative filtering algorithms on rating datasets using cross-validation and standard metrics (RMSE, MAE).","Prototype and tune recommender systems with grid search over algorithm hyperparameters before deploying to production.","Analyze algorithm performance on Movielens or Jester datasets to understand baseline behavior and algorithm trade-offs.","Build custom recommendation algorithms by extending the library's base classes and integrating them into the evaluation framework.","Benchmark matrix factorization and neighborhood-based methods on your own explicit-rating datasets."],"what_it_does":"Scikit-surprise is a Python library for building and analyzing recommender systems that work with explicit rating data. It provides a collection of ready-to-use prediction algorithms\u2014including SVD, matrix factorization variants (PMF, SVD++, NMF), k-NN methods, baseline algorithms, and co-clustering\u2014along with built-in similarity measures and tools for cross-validation and hyperparameter tuning. The library is designed to give users control over experiments through clear documentation and easy dataset handling, supporting both built-in datasets (Movielens, Jester) and custom data.\n\nThe package depends on joblib, numpy, and scipy for its core numerical and parallelization operations. It is actively maintained, supports Python 3.10 through 3.14, and is distributed as precompiled wheels for macOS, Linux, and Windows. The library does not support implicit ratings or content-based information, focusing instead on explicit rating prediction tasks.","worth_installing":"Yes. Scikit-surprise is a mature, actively maintained library (Production/Stable status, 6806 stars, recent release) with no known security vulnerabilities, permissive licensing, and solid support for modern Python versions. It is the standard choice for explicit-rating recommender system research and prototyping. Install it if you need to build, evaluate, or compare collaborative filtering algorithms; skip it only if you require implicit feedback or content-based methods."},"id":"scikit-surprise","links":{"html":"https://skillfed.io/packages/scikit-surprise","md":"https://skillfed.io/packages/scikit-surprise.md","pypi":"https://pypi.org/project/scikit-surprise/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-05-30","license_spdx":null,"license_treatment":"permissive","name":"scikit-surprise","python_support":"supports_current","summary":"An easy-to-use library for recommender systems."},"popularity":{"monthly_downloads":119875,"position":12052,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"1.1.5"}