Home // ICIW 2016, The Eleventh International Conference on Internet and Web Applications and Services // View article

A XBRL Financial Virtual Assistant

Authors:
Adalberto Alves Abraão
Paulo Caetano da Silva

Keywords: Virtual Assistant; XBRL Financial Virtual Assistant; Financial Virtual Assistant; LDQM application; NLP application; Virtual Financial Assistant Architecture; Architecture for Virtual Closed Domain Assistants

Abstract:
Nowadays, by means of stock exchanges, it is possible to invest in globally located enterprises. It is a market in which it is possible to obtain great profits, but it also conveys great risks of loss. In order to decrease risks, it is important to know the financial strength of the enterprises, through specific indicators, to ask what their values are, for example, “What is the leverage ratio of the company X currently?”. Financial consultancy emerges for that need, but it is very expensive. An alternative is to search for the answers by themselves on enterprises websites or from the regulatory agencies. Such tasks require time, calculations and analyses. With the aim at facilitating the obtaining of financial information about the enterprises for any investors, a virtual financial assistant is presented in this paper which answers to the questions of financial type made by the user, interacting by means of a natural language. The assistant utilizes financial information from analytic Online Analytical Processing (OLAP) queries at eXtensible Business Reporting Language (XBRL) database. The architecture of the virtual assistant is presented as well as details a prototype's implementation. As a result, we expect that the assistant correctly answers the user’s questions, asked in a natural language and related to financial indexes of given enterprises.

Pages: 64 to 72

Copyright: Copyright (c) IARIA, 2016

Publication date: May 22, 2016

Published in: conference

ISSN: 2308-3972

ISBN: 978-1-61208-474-9

Location: Valencia, Spain

Dates: from May 22, 2016 to May 26, 2016