Home // eKNOW 2022, The Fourteenth International Conference on Information, Process, and Knowledge Management // View article

Towards a Going Concern Assessment Pipeline

Authors:
Lotte Verhoeven
Eric Mantelaers
Martijn Zoet

Keywords: Forecasting algorithms; Continuity; Going Concern; Forecasting; PyCaret.

Abstract:
The assessment of the going concern analysis in the audit process is based on the professional judgment of the auditor. To support this individual and personal judgment of the auditor, a more direct source of information in the form of an automated going concern analysis could provide a solution. In this paper a method to automate the going concern analysis was set up, using a combination of 16 forecasting algorithms. To build and validate the forecasting algorithms, 225 administrations have been divided in a train and test set. The results show a confidence percentage of 97.45% for the Gradient Boosting Regressor model, 96.79% for the Decision Tree Regressor model and 77.72% for the AdaBoost Regressor model on the basis of the condition current liabilities for Administration 1.

Pages: 7 to 11

Copyright: Copyright (c) IARIA, 2022

Publication date: June 26, 2022

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-986-7

Location: Porto,Portugal

Dates: from June 26, 2022 to June 30, 2022