FinKG: A Core Financial Knowledge Graph for Financial Analysis

Natthawut Kertkeidkachorn, Rungsiman Nararatwong, Ziwei Xu, Ryutaro Ichise

Abstract: 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.