FinKG: A Core Financial Knowledge Graph for Financial Analysis
FinKG: A Core Financial Knowledge Graph for Financial Analysis
复制标题
DOI：
10.1109/icsc56153.2023.00020
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Natthawut Kertkeidkachorn;Rungsiman Nararatwong;Ziwei Xu;R. Ichise
中科院分区：
文献类型：
--
作者：
Natthawut Kertkeidkachorn;Rungsiman Nararatwong;Ziwei Xu;R. Ichise
金融知识图通常是通过使用大量数据自动构建的，没有定义良好的本体。本体的缺失导致推理能力的下降。此外，自动构建的知识图还存在质量问题。因此，在本文中，我们引入了一个核心金融知识图，即FinKG。我们的目标是构建一个定义良好的本体的高质量金融知识图谱。本体是基于美国证券交易委员会(SEC)提供的公共数据以及公开交易所市场数据手动构建的，并由金融专家进行验证。此外，我们还通过两个应用：知识检索和股票价格预测，证明了FinKG的有效性。知识检索揭示了实体之间的复杂联系，而FinKG的聚合特征有助于神经模型更好地预测股价。
Financial Knowledge Graphs are usually automatically constructed by using a large amount of data without a well-defined ontology. Lacking ontology results in degrading reasoning ability. Moreover, automatically constructed knowledge graphs suffer from the quality issues. In this paper, we therefore introduce a core financial knowledge graph, namely FinKG. Our goal is to construct a high-quality financial knowledge graph with a well-defined ontology. Ontology is manually crafted based on public data provided by U.S. Securities and Exchange Commission (SEC) together with open exchange market data and is verified by the financial expert. Furthermore, we demonstrate the usefulness of FinKG with two applications: knowledge retrieval and stock price prediction. Knowledge retrieval reveals the complex connection among entities, while aggregated features from FinKG help neural models to better forecast stock prices.