{"adoption": {"forks": 177, "observed_at": "2026-08-28T04:03:36.398992+00:00", "stars": 1105}, "canonical_url": "https://ross.abutalabs.com/products/datasets-for-recommender-systems", "card": {"archived": false, "artifact_type": "dataset", "description": "This is a repository of a topic-centric public data sources in high quality for Recommender Systems (RS)", "domain": ["data-science", "machine-learning"], "enriched": true, "function": ["data-science"], "health_score": 20, "homepage": null, "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["caserec/Datasets-for-Recommender-Systems"], "name": "caserec/Datasets-for-Recommender-Systems", "platform": ["cross-platform"], "pushed_at": "2023-08-28T21:59:23+00:00", "repo": "caserec/Datasets-for-Recommender-Systems", "stars": 1105, "tags": ["recommender-systems", "datasets", "curated-list", "public-data", "collaborative-filtering"], "topics": ["recommender-systems", "datasets", "public-data", "database", "data-science"], "urls": [], "use_cases": ["find datasets to benchmark recommender system algorithms", "download MovieLens-style rating data for collaborative filtering experiments", "get e-commerce click and purchase logs for recommendation research", "locate music listening datasets for implicit feedback models", "find pre-processed datasets for academic RS papers"], "what_it_is": "A curated collection of public datasets for recommender systems research, spanning domains like books, movies, music, e-commerce, and dating. It links to well-known sources such as MovieLens, Amazon reviews, and LastFM, with descriptions and some pre-processed academic variants.", "when_to_avoid": ["you need a software library or tool rather than data", "you require guaranteed open licenses - some listed datasets need permission or citation", "you need actively maintained or freshly updated datasets"], "when_to_choose": ["you need real-world rating or interaction data to train or evaluate recommendation models", "you want a quick index of well-known recommender system datasets across domains", "you are doing academic experiments and want pre-processed benchmark data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datasets-for-recommender-systems", "repo": "caserec/Datasets-for-Recommender-Systems", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:36.398992+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:44:21.274784+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "386ecf7fd6bab9d546b047140d4be689656cd67cdd347c59b80ecc73d2f68e37", "fetched_at": "2026-08-28T04:03:36.398992+00:00", "kind": "readme", "missing": false, "url": "https://github.com/caserec/Datasets-for-Recommender-Systems"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3496, "days_push": 1101, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}