Classification of capital expenditures and revenue expenditures: An analysis of correlation and neural networks

• المؤلفون الرئيسيون: Siraj, Fadzilah, Abu Bakar, Nur Azzah, Abolgasim, Adnan
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2009
• الموضوعات: QA76 Computer software
• الوصول للمادة أونلاين: http://repo.uum.edu.my/13573/1/PID256.pdf; http://repo.uum.edu.my/13573/; http://www.icoci.cms.net.my

The classification between the capital expenditures and revenue expenditures is one of the common problems in the accounting literature since it has a significant impact on financial statements.This study aims to analyze the correlation of classification model such as Neural Networks (NN) in order to develop a model that can be trained to recognize hidden patterns of the borderline between the two expenditures types, viz: the capital and revenue expenditure.Twelve criterions were identified in order to classify between the two expenditures types and a Backpropagation Learning was utilized in this study.The highest classification accuracy obtained by NN is 94.20%. Correlation analysis reveals a significant correlation between some identified criterions with the model’s target.Strong correlation between target and criterion LASMFY (0.532) indicates that any expenditure lasts for more than a fiscal year will be more probable to be classified into a capital expenditure.Also, criterion RESALE proves its strong influence, with correlation of (-0.874) which implies more probability of classification into revenue expenditure if any expenditure was spent for intent for resale. Medium correlation shown by criterion REGULR (-0.251) indicates a moderate probability of classification into revenue expenditure if expenditure was spent in a regular basis.