{"url":"/dataset/financial-dynamic-knowledge-graph","name":"Financial Dynamic Knowledge Graph","full_name":null,"description_markdown":"# FinDKG: The Global Financial Dynamic Knowledge Graph Dataset\r\n\r\nFinDKG is an open-source dataset focused on creating a temporally-resolved Financial Dynamic Knowledge Graph. Designed to bridge the gap in industry-specific knowledge graphs, particularly in the financial sector, FinDKG provides a high-touch, temporally-aware representation of global economic and market dynamics. This repository includes comprehensive details about the dataset, methodology, and schema, aiming to facilitate academic research and actionable insights in global financial markets.\r\n\r\n## Background \r\n\r\nWhile general-purpose knowledge graphs are abundant, industry-specific ones are comparatively rare, especially in the financial sector. FinDKG aims to fill this void by offering a resource for researchers and professionals looking to leverage knowledge graph technology in finance.\r\n\r\n\r\n\r\n## FinDKG Dataset\r\n\r\nThe dataset's foundation lies in an extensive news corpus curated to capture both qualitative and quantitative indicators in the financial landscape. We utilized the [Wayback Machine](https://web.archive.org/) to amass a dataset comprising global financial news. \r\n\r\n\r\n\r\n## Dataset Structure\r\n\r\n- Temporal Knowledge Graph (TKG) with daily-resolved event triplets\r\n- Event triplets are tagged with specific timestamps corresponding to their release dates\r\n- Training, validation, and test splits organized chronologically\r\n- Weekly aggregation of event triplets as the basic unit of time\r\n\r\n### Data Format\r\n\r\n**/FinDKG** is the default study dataset folder including the graph dataset and the corresponding data splits. The graph dataset is organized in the following structure:\r\n\r\n* 'train.txt', 'valid.txt', and 'test.txt': The first four columns correspond to subject, relation, object, and time. The fifth column is ignored.\r\n\r\n* 'stat.txt': The first two columns correspond to the number of entities and relations, respectively.\r\n\r\nTest set is held-out for evaluating the model performance. This should match the results of the original paper regarding the Temporal Link Prediction evaluation.\r\n\r\n**/FinDKG-full**: The full dataset including a larger size of the event triplets. This graph dataset adopts the same format as `/FinDKG` while is left for future extended research.\r\n\r\n* 'time2id.txt': This time mapping table further provided the mapping from time ID to realistic date for real-world application.\r\n\r\n\r\n\r\n\r\n## Usage\r\n\r\nThe dataset is designed for graph-based AI methods aiming to generate actionable insights in the financial domain. It is freely available for academic and research purposes. Refer details to our designated [FinDKG website](https://xiaohui-victor-li.github.io/FinDKG/).\r\n\r\n\r\n(Description from Dataset Repo)","description_withheld":null,"homepage":"https://xiaohui-victor-li.github.io/FinDKG/#data","introduced_date":"2024-07-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/findkg-dynamic-knowledge-graphs-with-large","title":"FinDKG: Dynamic Knowledge Graphs with Large Language Models for Detecting Global Trends in Financial Markets","first_author":"Xiaohui Victor Li","url":null},"license":{"name":"GNU General Public License v3.0 (GPL-3.0)","url":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Graphs","url":"/datasets/modality/graphs"},{"name":"Financial","url":"/datasets/modality/financial"}],"tasks":[{"name":"Node Classification","url":"/task/node-classification","datasets_with_task":"/datasets/task/node-classification"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Inductive knowledge graph completion","url":"/task/inductive-knowledge-graph-completion","datasets_with_task":"/datasets/task/inductive-knowledge-graph-completion"},{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"Graph Embedding","url":"/task/graph-embedding","datasets_with_task":"/datasets/task/graph-embedding"},{"name":"Financial Relation Extraction","url":"/task/financial-relation-extraction","datasets_with_task":"/datasets/task/financial-relation-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Financial Dynamic Knowledge Graph"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}