{"work":{"id":"1b87323d-bb68-4e84-943e-d0e080e5c3ad","openalex_id":null,"doi":null,"arxiv_id":"1603.02754","raw_key":null,"title":"XGBoost: A Scalable Tree Boosting System","authors":null,"authors_text":"T","year":2016,"venue":"cs.LG","abstract":"Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.","external_url":"https://arxiv.org/abs/1603.02754","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T06:30:23.920131+00:00","pith_arxiv_id":"1603.02754","created_at":"2026-05-10T03:29:21.131924+00:00","updated_at":"2026-05-25T06:30:23.920131+00:00","title_quality_ok":true,"display_title":"Chen and C","render_title":"Chen and C"},"hub":{"state":{"work_id":"1b87323d-bb68-4e84-943e-d0e080e5c3ad","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":25,"external_cited_by_count":null,"distinct_field_count":11,"first_pith_cited_at":"2024-08-01T19:31:04+00:00","last_pith_cited_at":"2026-05-19T12:12:24+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-26T05:06:14.496331+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"method","n":5},{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"use_method","n":5},{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}