Dataset
13f-institutional-holdings-sec-edgar
A consolidated, ready-to-use repository of 13F institutional holdings drawn from SEC EDGAR filings, capturing the most recent quarterly disclosures of more than 13,000 investment managers including hedge funds, mutual fund complexes, pension funds, banks, and family offices, with each record summarizing total assets under management and individual positions.
Data preview
Dataset card
A tabular dataset of 13,118 institutional investment managers built from SEC Form 13F filings on EDGAR, capturing each filer's most recent quarterly disclosure alongside derived behavioral scores. It is distributed as a CSV under a CC0 public-domain declaration.
What this dataset contains
Each row corresponds to a single 13F filer, hedge funds, mutual fund families, pension funds, banks, and family offices, captured at the latest reported quarter. Coverage follows the SEC threshold of roughly $100M in qualifying U.S. equity assets under management, with a reporting lag of up to 45 days after quarter-end. The file has 13,118 rows and is ranked by reported portfolio value.
Structure and fields
Key columns include cik, institution_name, category, manager_name, latest_period_of_report, total_value_usd, and total_holdings_count, identifying the filer and the size of the disclosure. Behavioral metrics are provided as concentration_score, turnover_score, momentum_contrarian_score, sector_conviction_score, diversification_score, and position_sizing_discipline_score, all stored as float64. A single train split is exposed with the full 13,118 rows.
How analysts use it
Long-only and hedge-fund analysts can screen the universe of 13F filers by size or behavioral tilt to identify candidates for position-level peer benchmarking or sentiment work. The behavioral scores support tabular regression and classification exercises on institutional style, while institution_name and cik enable joins against external EDGAR scrapes for stock-by-stock holdings. Distribution is limited to a single CC0 snapshot, so live quarter-over-quarter tracking requires a separate data source.
Documentation & references 1
Related datasets
Browse moreParsed eligibility criteria from 13,229 ClinicalTrials.gov studies representing the candidate pool gathered by two first-stage retrievers during TREC Clinical Trials 2021–2023, formatted as typed entity-relation graphs for reranking models.
The clinical-trials-patient-graphs dataset is a small tabular collection of patient-level clinical records distributed in Parquet format by the 2001jdev publisher. It organizes entities and relations extracted from trial data into structured rows spanning 2021 through 2023.
This dataset is a parsed snapshot of ClinicalTrials.gov records, distributed in Parquet format on the Hugging Face Hub under an unspecified license. It contains roughly 52,000 trial entries drawn from public registry filings.
clinical-trials-trec-qrels is a tabular relevance-judgment file distributed by the 2001jdev user on the Hugging Face Hub. It maps clinical-trial topic identifiers to NCT registry IDs with graded relevance scores.
The clinical-trials-trec-topics dataset is a small tabular collection of clinical-trial topic records distributed in Parquet format on the Hugging Face Hub. It appears to be derived from TREC clinical-trial retrieval topics, with rows partitioned by year.
SEC EDGAR 10-K & 10-Q financial statements for 2,600+ NASDAQ companies.
Discussion
Questions or observations about this dataset? Join the conversation on X.
No comments yet. Start the conversation on X.