Abstract
Annual Financial Reports are the core in the Banking Sector to publish its financial statistics. Extracting useful information from these complex and lengthy reports involves manual process to resolve the financial queries, resulting in delays and ambiguity in investment decisions. One of the major reasons is the lack of any standardization in the format and vocabulary used in the reports. An automated system for resolution of intelligent financial queries is therefore difficult to design. Several works have been proposed to overcome these problems using Information Extraction; however, they do not address the semantic interoperability of the reports across different institutions. This work proposed an automated querying engine to answer the financial queries using Ontology based Information Extraction. For Semantic modeling of financial reports, a Financial Knowledge Graph, assisted by Financial Ontology, has been proposed. The nodes are populated with entities, while links are populated with relationships using Information Extraction applied on annual reports. Two benefits have been provided by this system to stakeholders through automation: decision making through queries and generation of custom financial stories. The work can further be extended to other domains including healthcare and academia where physical reports are used for communication.
Highlights
Stakeholders seek information regarding company profile and its general financial standing before taking any decision though various channels
The required information is widely dispersed in the quarterly and annual reports declared by companies; it is difficult for investors to read and interpret the financial implications mentioned therein
Following are the major contributions of this work: (A) Integration of Information Extraction with Semantic Web (B) Proposed Financial Knowledge Graph to model the domain of Financial Systems (C) Mapping Financial Reports in the domain using Ontology (D) Extending manual financial reports as machine readable using Information Extraction
Summary
Stakeholders seek information regarding company profile and its general financial standing before taking any decision though various channels. Automatic information extraction from these financial disclosures is hard, owing to the lack of boundaries between the items to be extracted, context dependence of the targets entities, language pattern variations, and statistical methods limitations [1] Another problem in information extraction from these financial datasets is that these are usually available as non-structured texts or in PDF that involves meticulous manual preprocessing or application of sophisticated ETL (Extract, transform, load) tools in order to ingest data automatically [2] [3]. This step will be done manually for our research work and resulting data will be stored in separate text files for each entity. Following are the major contributions of this work: (A) Integration of Information Extraction with Semantic Web (B) Proposed Financial Knowledge Graph to model the domain of Financial Systems (C) Mapping Financial Reports in the domain using Ontology (D) Extending manual financial reports as machine readable using Information Extraction
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have