Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/70800

Accounting method selection using neural networks and multi-criteria decision making

File Size Format  
0153.pdf 491.98 kB Adobe PDF View/Open

Item Summary

Title:Accounting method selection using neural networks and multi-criteria decision making
Authors:Duan, Yang
Yeh, Chung-Hsing
Dowe, David L.
Keywords:Machine Learning and Predictive Analytics in Accounting, Finance, and Management
accounting method
accounting results
company strategic goals
multi-critiera decision making
show 1 moreneural networks
show less
Date Issued:05 Jan 2021
Abstract:The selection of accounting methods has significant impacts on companies’ accounting results and strategic goals. However, this selection problem has not been effectively addressed by existing studies. To fill this important gap, we propose a novel approach for evaluating two accounting method alternatives, namely Full Cost (FC) and Successful Effort (SE) with an empirical case of an oil and gas company. Neural networks (NNs), fuzzy multi-criteria decision making (MCDM) with optimal weighting are applied to evaluate the consequent effects of FC and SE on strategic goals of the case company. The empirical study conducted demonstrates the effectiveness of the proposed approach. Methodologically, this paper provides a structured approach for evaluating accounting method alternatives in a rational and informed manner. Empirically, the evidence obtained from applying the proposed approach can be used to support the case company’s decision on accounting method selection.
Pages/Duration:10 pages
URI:http://hdl.handle.net/10125/70800
ISBN:978-0-9981331-4-0
DOI:10.24251/HICSS.2021.188
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: Machine Learning and Predictive Analytics in Accounting, Finance, and Management


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons