Business Intelligence and Analytics to Prediction of Going Concern Using Neuro-Fuzzy Approach


Rapid advances in technology, enterprise environmental changes and increasing competition has affected the risk of investment. Going concern prediction (GCP) is an important element in investors' evaluation. The evaluation of a enterprise 's going concern status is not an easy task. To assist auditors, going concern prediction models based on statistical methods such as multiple discriminant analysis and multiple linear regression analysis have been explored with some success. Nowadays, the business intelligence and analytics (BI&A) has attracted more and more attentions, which is required to manage immense amounts of data quickly. However, current researches mainly focus on the amount of data. In this paper, the other two properties of BI&A, which include the high dimensionality of data, and the dynamical change of data, are discussed. This study attempts to look at a different and more recent approach XAdaptive Neuro Fuzzy Inference System (ANFIS). ANFIS has effectively solved many large-scale, and dynamical problems. This study explores and compares the usefulness of Multiple Linear Regression Analysis (MLRA), Classification and Regression Tree (CART) and proposed ANFIS in predicting an enterprise's going concern status. The sample data comprise financial ratios for 165 going concerns and 165 matched non-going concerns. The classification results from view of significance test and predictive accuracy which indicate the potential usefulness of BI&A in a going concern prediction context. These results also indicate that ANFIS shows acceptable performance in terms of accuracy and comprehensibility, and it is an appropriate choice for auditors to assess potential clients and as a means

Author Information
Yee Ming Chen, Yuan Ze University, Taiwan
Yu-Pu Chiu, Yuan Ze University, Taiwan

Paper Information
Conference: ACTIS2014
Stream: The Data-Enriched Society

This paper is part of the ACTIS2014 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

Comments & Feedback

Place a comment using your LinkedIn profile


Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by James Alexander Gordon