engleski

Accounting Journal Reconstruction with Variational Autoencoders and Long Short-term Memory Architecture

Our tries to learn machines how to reconstruct journal entries with the aim of finding anomalies lead us to deep learning (DL) technologies. Nowadays Variational autoencoder and Long short- term memory architectures as well as other deep learning architectures solves wide range of problems, yet they are not enough implemented in a field of accounting information systems (AIS). Inside AIS, accounting data follows accounting logic and makes specific datasets constructed by different type of columns - categorical and continuous variables. Our aim is reconstruction of these variables. Development of the model capable for precise reconstruction is not an easy task. This paper describes our research for anomaly detection model architecture which will be capable to reconstruct dataset with categorical features mixed with continuous monetary value feature. We developed basic models trained on accounting journals from 2007 to 2018 and then tested in the fiscal year 2019. Still, lots of hyperparameters need to be checked if we want to improve accuracy. Deep learning research is an engineering task leaded by experience so there is no linearity in the model improvement. Consequently, this paper is our contribution to collection of experience in developing accurate, useful and intelligent accounting control system.

general ledger ; journal entry ; bookkeeping ; accounting ; deep learning ; variational autoencoder ; long short-term memory ; anomaly detection ; accounting control system

nije evidentirano