论文部分内容阅读
个性化传播包括许多因素:市场营销策略,清晰的数据库,建立客户接触点的数据分析,针对客户接触点的相关市场策略的规则,对客户隐私的保护,文件输出,衡量成功的尺度和响应客户反馈的迭代设计。近年来,利用客户数据实现个性化传播已获得越来越多的关注。然而,利用精确的数学方法从客户数据中提取关系数据,然后将其转化为抽象的规则,并融入实际的设计,这与其说是一种科学技术,不如说是一种艺术。本论文主要探讨了如何有效地将通过数据挖掘得到的重要变量转化为具体的编程规则,以准确地表示这些可变数据,并应用到个性化传播中。
Personalized communication includes many factors: marketing strategy, a clear database, data analysis of customer contact points, rules of marketing strategies for customer touchpoints, protection of customer privacy, output of documents, measures of success and responsiveness to customers Feedback iterative design. In recent years, the use of customer data to achieve personalized communication has received more and more attention. However, using mathematical techniques to extract relational data from customer data and then translate it into abstract rules and incorporate them into the actual design is not so much a science as an art. This paper mainly discusses how to effectively translate the important variables obtained through data mining into specific programming rules to accurately represent these variable data and apply them to personalized communication.