Retail Customer Relationship Management Based On Data Mining

Because of the rapid development of information technology and global economic integration, the business environment has undergone tremendous changes, Also changing the way of the competition among enterprises. The traditional production-centric and the business strategy for the purpose of selling products is gradually being replaced by customer-centric and for the purpose of service-market. At this point, customer-focused, listening to the need of our customers, the ability to respond rapidly for the changes of customer expectations is becoming the key to business success. Therefore, enterprises must establish and strengthen long-term customer relationships, integrate the marketing, sales and service and other sectors, and provide a full range of services to customers and track, in order to maintain a high market share and customer loyalty. In this case, customer relationship management is coming, and quickly becomes a common focus of global business and theorists.This paper is divided into six chapters to study the technology strategy of the implementation of customer relationship management for retail. The first chapter introduces the background and significance of research for the paper, the main contents and methods, the innovation for the paper. The second chapter is theoretical analysis for customer relationship management for retail, including theoretical analysis of retail and customer value, the traceability and concepts of customer relationship management, the analysis of core competitiveness of enterprises and business environment for retail. The third chapter is the status and problem analysis for the implementation of customer relationship management for retail industry in China, including the need for the implementation of customer relationship management, the status and problem analysis for the implementation of customer relationship management for retail in China, the difficult of the retail enterprises to implement CRM in China. The fourth chapter introduces data mining algorithms and model analysis for customer relationship management in retail, including overview of data mining and customer segmentation model. The fifth chapter introduces the implementation of model for customer relationship management in retail, including clustering technology and its application in CRM, the implementation of matrix model of customer value and RFM indicators and methods for customer classification. Chapter 6 is full summary and outlook, describes the practice strategy of the implementation for customer relationship management for retail industry in China, describes the paper's inadequacies and prospects.This paper will use cluster analysis and neural network technology in data mining techniques to analyze customer information. First, get the required data from the data warehouse of the retail business, then filter, clean the data and convert, integrate the data into a single range for data mining, discover the information and knowledge. First, use K-means cluster analysis algorithm, making a reasonable breakdown of customers, customer service departments serve every customer focused, develop effective marketing strategies. Then use artificial neural network of the competitive type - self-organized competition. Based on RFM model, classify customers, first teacher-free learning, training data that has been classified, classifying the unclassified data, and then using the RFM model based on three indicators of frequency, spending and near degree to classify the customers.China's retail business must grasp the existing customers, strengthen customer team, get new customers, by identifying valuable customers and mining customer information to make decisions, Increase customer's value, satisfaction, profit contribution and loyalty, find the new markets and channels for the need of expansion for enterprises to maximize profits. Enterprise need focus on data mining technology at the beginning, targeted potential customers, by analyzing the existing customers and the marketing activities that have been taken to find those most likely to become customers of the enterprise, to take appropriate means and channels to effectively impress them, at the same time to assess the business benefits. After the study period, into the formation, the customer has purchased the company's products and services, but the frequency of use and spending are likely low, we try to use data mining techniques to encourage customers to buy more products and services. Cross-sell and increase customer purchases, through the use of clustering technology to help companies find people with similar buying behavior and preferences of customers, and further enable these customers to produce high value. Then, into the stable time, high-quality enterprises should prevent loss of high-quality customers, also to use data mining techniques to take certain measures to retain customers that possible to lose. Throughout the life cycle of customers, companies should continue to use data mining technology to analyze customer value, to guide business operations.