Financial Application of Neural Networks: Two Case Studies in Greece

摘要: In the past few years, many researchers have used Artificial Neural Networks (ANNs) to analyze traditional classification and prediction problems in accounting finance. This paper explores efficacy of ANNs detecting firms that issue fraudulent financial statements (FFS) predicting corporate bankruptcy. To this end, two experiments been conducted using representative algorithms. During first experiment, algorithms were trained a data set 164 fraud non-fraud Greek recent period 2001-2002. second 150 failed solvent 2003-2004. It was found could enable experts predict bankruptcies with satisfying accuracy.