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

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.