Research And Application Of Customer Information In Crm Based On Data Mining

With the rapid development and wide application of information technology, many enterprises have accumulated huge amounts of data. Traditional data processing methods cannot make full use of the data embedded in these useful information. Data mining technology is a new solving method to such problems.Applying the knowledge of customer information by data mining to guide marketing activities is an important application of technology. According to different categories of enterprises, the marketing cost could be 5% to 25% of total product cost. How to effectively use the marketing budget is significant to make a business being profitable. It is a very important trend of database technology to use the measurable data to break down the segment market and expand the business market.This paper builds up a dimensional model on customer database of training institutions. Using the cloud computing method, basing on Google API to process customer information of their addresses, we get the accurate geographic information of latitude and longitude. Then making full use of these geographic information as the benchmark, a modified data mining algorithm is used to do the cluster analysis. Finally, we developed the program module to make the visible results by using the Google API map. All the analysis results are displayed on the map. This could help marketing decision makers have the intuitional market idea, and improve the efficiency of marketing activities. Besides, the analysis results can also help to verify the rationality of training spots placing. Furthermore, it can help to analysis and verify the model and mining results of current marketing methods, and realize the marketing advertisement target by optimizing and adjusting the real marketing steps.The analysis model based on Google API and cluster mining method can process all kinds of information such as customer addresses, so that it could be applied in B2C industries (directly facing the end users) like retail industry, banking and insurance, fast consumer goods, and telecommunication and so on. It is also very valuable for chain sector to place their ends. The method and the model we proposed can be expanded to develop more data analysis methods, like segmentations of customer analysis, features of customer mobility etc.