Artificial neural network models for predicting patterns in auditing monthly balances

The aim of this study is to investigate the potential of artificial neural network (ANN) models to recognise patterns when auditing monthly balances in financial accounts. ANNs have been used in many different disciplines as a basis for building intelligent information systems. This study examines the predictive ability of an ANN by building models using the 72 monthly balances of a manufacturing firm. The monthly balances are regarded as a time-series and the target is to recognise the dynamics and the relationships between different accounts. Furthermore, a certain seeded material error with signals from the ANN model is investigated. The results achieved indicate that neural networks seem promising for recognising the dynamics and the relationships between financial accounts.