The Application Of Data Mining Algorithm To Administrative Audit

Data mining extracts implicit, previously unknown and usable knowledge from large amounts of data. It is one of the frontiers of research in the fields of database and DSS. The data mining technique has been widely used in various fields recently.This paper mainly studies the application of data mining algorithm to administrative audit and puts forward a viewpoint that the data mining method should be combined with the concrete application field. Besides, the paper introduces the association rule method and outliers mining and proposes a solution to the practical problem. So far, the results of the research have been applied in practice.The work is briefly summarized as follows:Set forth the CRISP-DM mining methods to solve practical problems. Define a XML-based data mining application modeling platform to describe the phases of the process Module.Determine the user requirement in the administrative audit data miner. Apply Multi- dimensional association rule audit data mining method (MulitDim-Adm)and outliers audit data mining method(SAOM) to solve the practical problems and display the corresponding experimental results with the actual data.Realize a useful data mining system. According to the general process of the data miner, the system divides the whole data mining task into five parts, including data integration, data preparation, data exploration, mining algorithm and result exhibition. The five parts associates with each other through the parameters with the help of the advanced XML technique. The system is highly expansible.