|
Title:
|
FINANCIAL DATA EXTRACTION AN APPLICATION |
|
Author(s):
|
Hassan Alam, Aman Kumar, Cheryl Lee, Rahul Kumar, David Ju |
|
ISBN:
|
978-989-8704-10-8 |
|
Editors:
|
Ajith P. Abraham, Antonio Palma dos Reis and Jörg Roth |
|
Year:
|
2014 |
|
Edition:
|
Single |
|
Keywords:
|
Financial data extraction, Machine Learning application, Naïve Bayesian classifier |
|
Type:
|
Short Paper |
|
First Page:
|
227 |
|
Last Page:
|
231 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In this study we have developed a financial data extraction system to tag and extract financial concepts along with corresponding numeric values monetary and temporal. We employ machine learning and natural language processing methods to identify financial concepts and link them to numerical entities based on the tagged financial data. While large number of US companies is required to tag (US-GAAP1 tags) part of their financial statements filed to the US Security and Exchange Commission quarterly and yearly, only part of the worldwide financial information is tagged. In preliminary evaluations based on publicly available 10-Q2 and 10-K3 documents, the system records an average module-wise accuracy of 87% toward financial concept identification and semantic tag prediction. |
|
|
|
|
|
|
