融入情境强度的客户行为模式挖掘及变化侦测  

Customer behavior pattern mining and change detection with context intensity constraints

作　　者：琚春华[1,2] 帅朝谦[1] 

机构地区：[1]浙江工商大学计算机与信息工程学院,杭州310018 [2]浙江工商大学现代商贸研究中心,杭州310018

出　　处：《管理科学学报》2014年第8期60-73,共14页Journal of Management Sciences in China

基　　金：国家自然科学基金资助项目(71071141);国家科技支撑计划子课题资助项目(2012BAI34B01-5);浙江省自然科学基金资助项目(LY14F020002)

摘　　要：现有的客户行为分析往往忽略了客户群体的情境信息,使得行为模式及其变化分析存在局限性.文章首先定义了客户的情境、情境强度和行为变化,并对其进行了量化处理;其次,提出了融入情境强度约束的行为模式挖掘方法和模式变化侦测方法,并进一步提取了造成行为变化的关键情境.文中对情境强度的考虑,使得规则变化的敏感度加大,改进了海量数据稀疏下关联规则支持度、置信度和敏感度低的缺点.实验和分析证明了方法的可行性和有效性.Currently, many studies dedicated to context aware based recommendation, considered different types of context properties, but they ignore the important degree of different context attribute impact the behav- ior, that is, context strength. This paper defines the customer context, context intensity, and behavior chan- ging quantitatively; presents context strength constrained pattern mining methods and change detecting method to extract the critical situation caused by changes in behavior. The proposed algorithm increased the sensitivity of the interests changing, improvement of the massive data under support for sparse association rules, the shortcomings of low confidence sensitivity. Experiments and analysis demonstrated the feasibility and effective- ness.

关 键 词：情境强度 客户行为 约束频繁模式 变化侦测 推荐策略 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]