Web-Based Financial Disclosures by Using Machine Learning Analysis: Evidence from Bahrain

Sarea A. M., Subramanian S., Alareeni B. A.

in: Studies in Computational Intelligence, Springer International Publishing Ag, pp.357-371, 2021 identifier

  • Publication Type: Book Chapter / Chapter Research Book
  • Publication Date: 2021
  • Doi Number: 10.1007/978-3-030-62796-6_21
  • Publisher: Springer International Publishing Ag
  • Page Numbers: pp.357-371
  • Keywords: Bahrain Bourse (BB), Machine learning, Python programming, Regression analysis, Web-based financial disclosures (EFD)
  • Middle East Technical University Northern Cyprus Campus Affiliated: Yes

Abstract

This paper examines Electronic Financial Disclosure (EFD) by using machine learning analysis in listed firms in Bahrain bourse. Using machine learning techniques in Python Programming analysis is adopted to measure the effect of: Age, Liquidity, Leverage, Size, Industry and Profitability on the Electronic Financial Disclosure (EFD) through the Website of each firm listed in Bahrain Bourse (BB). The advantages of EFD is to predict better relation in firm characteristics and level of disclosure in banking sector in Bahrain. Which lead us to investigate the EFD by using machine learning analysis techniques. Further, in this research the sample size consists of all listed firms in Bahrain Bourse (BB) during 2017. The main finding is that profitability factor is having highest impact on the level of Electronic Financial Disclosure (EFD) which has been tested and predicted using machine learning. The implication of this paper helps firms in Bahrain to increase the level of (EFD) to reach full Web-Based Financial Disclosures to satisfy the stakeholders.