{"adoption": {"forks": 649, "observed_at": "2026-08-28T04:05:34.011226+00:00", "stars": 1770}, "canonical_url": "https://ross.abutalabs.com/products/kaggle-crowdflower", "card": {"archived": false, "artifact_type": "learning-resource", "description": "1st Place Solution for CrowdFlower Product Search Results Relevance Competition on Kaggle.", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "search-engine", "machine-learning", "data-science"], "health_score": 20, "homepage": "https://www.kaggle.com/c/crowdflower-search-relevance", "language": "C++", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["ChenglongChen/kaggle-CrowdFlower"], "name": "ChenglongChen/kaggle-CrowdFlower", "platform": ["python", "cpp", "cli"], "pushed_at": "2021-09-25T02:32:49+00:00", "repo": "ChenglongChen/kaggle-CrowdFlower", "stars": 1770, "tags": ["kaggle", "competition-solution", "search-relevance", "semantic-similarity", "xgboost", "feature-engineering", "ensemble-learning", "natural-language-processing", "search"], "topics": ["kaggle-crowdflower", "search-relevance", "natural-language-processing", "nlp", "kaggle-competetion", "relevance-competition", "semantic-matching", "kaggle", "search-engine", "product-search", "crowdflower", "semantic-similarity"], "urls": [], "use_cases": ["predict search results relevance for product queries", "learn how to win a kaggle nlp competition", "build semantic matching features for query-product pairs", "ensemble multiple model submissions for better scores", "study feature engineering for text relevance tasks", "reproduce a winning xgboost linear booster solution"], "what_it_is": "The 1st place winning solution code for the CrowdFlower Search Results Relevance competition on Kaggle. It provides a full pipeline for feature extraction, XGBoost model training, and ensemble selection for predicting search result relevance.", "when_to_avoid": ["you need a production-ready or maintained search relevance library", "you want a clean modular framework (the author recommends the Kaggle_HomeDepot repo instead)", "you need actively supported software with a license"], "when_to_choose": ["you want to study a proven top-ranked approach to search relevance prediction", "you need a reference pipeline for text feature engineering and model ensembling in Kaggle competitions", "you are working on product search relevance or semantic similarity problems"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/kaggle-crowdflower", "repo": "ChenglongChen/kaggle-CrowdFlower", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.011226+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:26:02.104180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7455d5684ca9497c0ff1a402330aae39d0a3c58c304857a72ae3bb5966dc3cef", "fetched_at": "2026-08-28T04:05:34.011226+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ChenglongChen/kaggle-CrowdFlower"}, {"content_hash": "36ce1a366e8ed01dd1e186f05e4a7a46a2b8ea05180999a61b49cae06b50378d", "fetched_at": "2026-08-29T11:04:19.701317+00:00", "kind": "homepage", "missing": false, "url": "https://www.kaggle.com/c/crowdflower-search-relevance"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:39:23.370411+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": 4070, "days_push": 1804, "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}}