To Achieve The Design Of Data Warehouse And Data Mining Technology In The Banking Industry

With the rapid development of the global Internet economy, the ITFIN, online shopping, online banking, and other e-commerce are developing rapidly. In the booming economic growth in China, the bank customer service sectors are experiencing severe challenges. After the baptism of the Internet revolution, the foreign bankshas begun to gain an advantage in the electronics, networking aspects when they stationed in the Chinese market. China Internet financial markets has both a huge market and the most serious challenges. In addition, with the development of computer hardware and software technology, data warehousing(DW), data mining(DM) technology gradually mature. While the financial sector opens now, the industry is more competitive and has put forward higher requirements for information technology. Bank information technology course has gone through three phases: business information, data centralization, information management technology. Most banks have completed the data centralization- second course. The bank information management becomes very urgent, data warehousing and data mining techniques provided technical support platform for bank management information.Currently, most of the banking sector’s data warehouse implement input, modify, statistic, data query and other functionsefficiently, but it cannotoptimize data relationships and rulesfriendly. Also it can not classification analyze according to the existing data or predict future trends more accurately.Therefore, the studies extracting valuable knowledgefrom the large amounts of data intelligently and effectively, namely,datamining,have practical significance and broad application prospects.Faced with the status of most banks can not deeply excavate the existing knowledge and the internet financial environment, this paper optimizes source data in conversion module of ETL whole process. It presents a better KNN algorithm to make data further consolidation and screening before the step of data mining. Then it proposes the point of view of bank data in data mining algorithm optimization, it uses the dual optimization Pro-Apriori decision tree algorithm to judge and predict after classifyingdata mining, which is more convenient to process the problem of knowledge acquisition from banking big data. Thesis have some guidance and advice and learn significance on aspects of the implementation of China’s banking industry data warehousing, structured data mining techniques, finance product planning, improving customer segmentation, dynamic analysis of market demand, strengthen customer relationship management and sales analysis.