Data Mining for Library Borrowing History Records

Abstract

Data mining is a hot research topic in the database community. With the emergence of new applications, the information discovered from the mining will be useful for business management and decision support. In this paper, we propose the idea of the weighted sliding window and apply it on the research of library data mining, based on the well-known Apriori algorithm. The weighted sliding window model allows the user to specify the range of data, the number of windows, the size of a window, and the weight of each window. The approach of allowing users to specify a higher weight for more significant data will make the mining result closer to the user’s requirement. We also apply the idea of the weighted sliding window on the consideration of the relationships among sequential borrowing records for a user, based on the well-known AprioriAll algorithm. Besides, the factor of peers is considered in the recommendation, in order to provide more information to users.