A Meta-Analysis of the Application of Artificial Neural Networks i nAccounting and Finance

Artificial Neural Networks (ANNs) have emerged as a robust technique of forecasting and prediction in almost every part of the business. This study explores the development of ANNs over a period of time and provides an extensive and exhaustive literature review on the applications of ANN in various fields of accounting and finance, such as stock market prediction, bankruptcy, and many others. The findings of the study support the superiority of the ANN model over conventional statistical techniques in prediction, such as Linear Discriminant Analysis (LDA), Logit Model, etc. However, determining the optimal architecture of an ANN model is a time consuming and difficult process. The novelty of this study lies in the fact that there is a dearth of literature on applications of ANNs in some sub-areas of accounting and finance, namely time series forecasting, specifically in foreign exchange and commodity markets. Thus, ANN application can be explored in these sub-areas of accounting and finance.