SoftwareX 9, pp. 308-316.
ISSN/ISBN: Not available at this time. DOI: 10.1016/j.softx.2019.04.004
Abstract: To apply the fuzzy support vector machines algorithm to the audit of XBRL (eXtensible Business Reporting Language) documents, sufficient data is unavailable. Thus, the objective of this study is coding a smartphone app named by aXBRL to provide such data. It is created to evaluate the conformity of XBRL instance documents to Benford’s law. Owning ACL and IDEA to implement the same task is too expensive. Applying the Excel to parse XBRL instance documents is slow because of correct XBRL taxonomies. The aXBRL app can be executed without any XBRL taxonomy. Data collected by it suggest that the price-to-book ratio versus equity ratio may be used to find out more possibly fraudulent XBRL instance documents. The misclassification rate is less than 30%. This misclassification rate encourages the integration of aXBRL app with fuzzy support vector machines models in a previous project. In conclusion, the aXBRL app brings a new application of fuzzy support vector machines algorithm. It can be used to increase the efficiency of searching fraudulent XBRL instance documents.
Bibtex:
@article{,
title = "aXBRL: Search of fraudulent XBRL instance documents with an Android app",
journal = "SoftwareX",
volume = "9",
pages = "308--316",
year = "2019",
issn = "2352-7110",
doi = "10.1016/j.softx.2019.04.004",
url = "http://www.sciencedirect.com/science/article/pii/S2352711018302334",
author = "G.Y. Sheu",
}
Reference Type: Journal Article
Subject Area(s): Accounting