文章基本信息

标题：A Survey Report on RFM Pattern Matching Using Efficient Multi-Set HPID3 Algorithm
本地全文：下载
作者：Priyanka Rani ; Nitin Mishra ; Samidha Diwedi Sharma 等
期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2013
卷号：4
期号：5-1
出版社：Seventh Sense Research Group
摘要：with the increasing contest in the retail industry, the main focus of superstore is to classify valuable customers accurately and quickly among the large volume of data. In this paper a survey report on proposed HPID3 classification algorithm is presented. It creates an innovative decision tree structure in order to predict the future outcomes. This technique proofs better over existing efficient techniques of classification, which had been proposed in recent times. In this proposed technique, concept of Recency, Frequency and Monetary is introduced, which is usually used by marketing investigators to develop some marketing rules and strategies, to find important patterns. Conventional ID3 algorithm is modified by firstly horizontally splitting the sample of RFM dataset and then some mathematical calculations are applied in order to construct decision tree and then to predict future customer behaviors by matching pattern. This proposed algorithm significantly reduces the processing time mean absolute error, relative absolute error and memory space required for processing the dataset and for constructing decision tree. The technique works optimally for small and large size database. The performance of the proposed algorithm is analyzed by the standard RFM dataset and compared with the conventional ID3 algorithm using weka data mining tool where the results are better for the proposed technique.
关键词：A Survey Report on RFM Pattern Matching Using Efficient Multi-Set HPID3 Algorithm