Research And Application Of Management Analysis System With Data Warehouse Supported

Data Warehouse is a technology of constructing enterprise information system, which is a new development in recent years, and it can change the collected date into analytical meaningful information. The information systems of enterprises structured by data warehouse technology can make information platform of enterprise development into data environment of system, instead of originally taking single data base as center data environment, and can offer the commercial decision support information for enterprise. With the development of economic and who joining WTO, the competition in telecommunication trade is aggravating day by day. To adapt to the fierce competitive environment of market, we should fully utilize a large number of valuable datum resources produced by business support systems, and draw useful information from these data, so as to realize intellectuality in message processing and offer the prompt, accurate, scientific decision support for market management. It is imperative that use data warehouse technology to structure telecom business analysis system. This paper introduces briefly the basic theory and methods, used the background of some mobile telecommunication company's Manage and Analysis System, and elaborates the building of data warehouse system from data warehouse and OLAP the two part, especially told the design and operation process of ETL part .The system help the customer to get business information effectively and timely from huge data source. It has steadily effect after being used, this is a good model for the design of likely system. In use of this system for data mining, the paper use a case that classifying arithmetic is used in analyzing subscriber's outline. It combines the ideas of system clustering arithmetic and method based on data density by input the method based on data density into ideas of system clustering arithmetic .The capacity of cleanse noise data has been enhanced than before. It got the goal of classify subscribers in practice better than before.