RETRACTED ARTICLE: Data mining optimization model for financial management information system based on improved genetic algorithm

• Published in: Information systems and e-business management Vol. 18; no. 4; pp. 747 - 765
• Main Authors: Li, Wei, Zhou, Qiling, Ren, Junying, Spector, Samantha
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2020; Springer Nature B.V
• Subjects: Business and Management; Information Systems Applications (incl.Internet); IT in Business; Management; Original Article; Clustering analysis; Model optimization; Financial management system; Data mining; Genetic algorithm
• ISSN: 1617-9846; 1617-9854
• DOI: 10.1007/s10257-018-00394-4

The traditional corporate financial diagnosis method is susceptible to the choice of accounting policies, and there are serious lags, one-sidedness and limitations. A financial management information system based on improved genetic algorithm is proposed based on the financial management information system data mining and clustering analysis model framework, and based on the financial analysis related knowledge. By adopting the event-driven architecture, a financial management information system model based on data mining technology is constructed, which not only enables the data warehouse and data mining technology to play a role in decision support, but also enables the financial information and non-financial information of enterprises to be fully utilized. By extracting financial data, using the above decision tree classification algorithm for data mining, classifying tests according to subject categories and business processes, and evaluating the accuracy of the prediction results, and then determining whether the classification algorithm is selected. The test and analysis of the national tax financial analysis system were completed, and three public data sets and three national tax financial expenditure data sets were selected, and the algorithm was tested on the experimental platform. The test results show that the algorithm show good performance for large-scale data sets, especially financial expenditure data sets, and the test accuracy rate is not only stable but also maintains a relatively high range.