Applying Multiple Linear Regression and Neural Network to Predict Business Performance Using the Reliability of Accounting Information System

Applying Multiple Linear Regression and Neural Network to Predict Business Performance Using the Reliability of Accounting Information System

Ahmed H. Al-Dmour (Brunel University, London, UK) and Rand H. Al-Dmour (The University of Jordan, Amman, Jordan)
Copyright: © 2018 |Pages: 15
DOI: 10.4018/IJCFA.2018070102

Abstract

This article aims to predict business performance using multiple linear regression and neural network. It compares the accuracy power of ANN and multiple linear regression (MLR) using the reliability of accounting information system as independent variables, and business performance as a dependent variable. It is based on primary data collected through a structured questionnaire from 162 out 202 of public listed companies in financial service sector in Jordan. The data were analysed using ANN and MLR. Testing results of the two methods ANN and MLR confirmed that the business performance indicators (financial, non-financial and combined) were significantly could be predicted by the reliability of AIS and they also revealed that in terms of predictive accuracy test, the ANN has a higher accuracy than regression analysis.
Article Preview
Top

2. Literature Review

Accounting Information System (AIS) has been recognised as one of the most important tools for measuring and reporting the activities and the profitability of the business organizations (Mansour, 2016). The real importance of adopting and use of information technology in the structure of AIS comes from the fact that it redesigned the internal AIS financial control in the direction of promising larger operational efficiency, it aligned the company’s functions to meet the needs of e-business, as well as it resulted in an objective and trustful performance. However, this heavy reliance of today’s businesses on the use of information technology makes the reliability of their AIS very critical.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 2 Issues (2021): Forthcoming, Available for Pre-Order
Volume 7: 2 Issues (2020)
Volume 6: 2 Issues (2019)
Volume 5: 2 Issues (2018)
Volume 4: 2 Issues (2017)
Volume 3: 2 Issues (2016)
Volume 2: 2 Issues (2015)
Volume 1: 2 Issues (2014)
View Complete Journal Contents Listing