Computational accounting in determining Chart of Accounts using nominal data analysis and concept of entropy

A new application of nominal data analysis to computational accounting system is introduced. ''Chart of Account " (COA), the structure of the Enterprise Requirement Planning (ERP) Accounting System is used as a nominal dataset enabling nominal feature selection technique be used to determine the close-optimal number of accounting segments. Five datasets are simulated with entropy measurement using the method of SUD. Self-Organizing map (SOM) is used to investigate the similarities among different segments , which proved to be a useful approach in cross-examining the COA structure. The obtained results show that they are promising from both computation and accounting perspectives. Data mining has practical significance in many areas such as bioinformatics, statistics, pattern recognition, machine learning because it is the principle of dealing with large amounts of data and picking out related information. It is increasingly used in extracting information from the enormous data sets generated by modern experimental and observational methods. For instance, in the example of cancer-causing gene selection, numerical feature selection scheme is used to determine the dominant genes (features) from a given huge dimensions of a dataset with over tenth of thousands of features. Computational accounting, which includes financial accounting, managerial accounting and planning and control, is also an important application. An Enterprise Requirement Planning (ERP) Accounting System is necessary for all medium and large size corporate company. The ERP Accounting System is used to reduce laborious manual work that results in an increase of the integrality in accounting sense. The foundation of the system is called the ''Chart of Accounts " (COA) that is a primary and structural block consisting of a series of segments in numerical digits. In accounting principal, at lease two lines are used to record one transaction. One line represents a credit item, whose name is replaced by a code, and another line represents a debit item; the two lines must be equal for balancing. For example, in a case when a company purchases a computer server, Table 1, in which the code ''300020 " represents ''Inventory " , and the code ''500010 " represents ''Liability " , is used as the basic data input system. The numerical data shown in Table 1 is a three segments COA structure (Oracle General Ledge User Guide, 2003). This three-segment structure is the foundation of the COA structure nowadays. The COA structure is the key for the ERP implementation; it is the first step …