Clustering Algorithm For The Library Interlibrary Loan System

Library, a service agency collecting and providing literature, from the very beginning, is used by people for acquiring knowledge. While, Interlibrary loan, as the earliest method of information co-sharing, has made great contribution to the development of library. Since CALIS has been explored many years, a great deal of data is accumulated and how to make them benefit for the development of library itself and interlibrary loan become the researching purpose of this paper. Data mining skill, searching for hiding information from the huge data, appearing from the late 80s of 20c, is quite a key for the research. In recent years, KDD has been held every year to accelerate its application process. In this paper, Clustering algorithms is explored for data analysis while, SimpleKMeans of WEKA which is an open source data mining platform for Data Mining.This paper introduces the Data Mining skill and Clustering algorithms and gives a detailed analysis of CALIS. Using SimpleKMeans, the paper mined and analysis the user, cost and item tables, to promote the valuable suggestion for the library, adjustment of H.R and Interlibrary loan, for example, according the analysis, the published to be purchased can be listed; Considering the workload of staff, recruitment schedule can be suggested; Based on the transaction time, users'preference can be clear. When cluster analysis, even the same algorithm is explored, the different analysis concerns make the different of outcome. Some concerns the largest proportion of cluster; others, while, concerned about the smallest, but the largest number of clusters. Based on this, making a corresponding application for the specific analysis to get results is required. Basically, this paper has managed to achieve the researching goal, acquiring the reasonable data and countermeasures.