Abstract：Book Recommendation Using Machine Learning Methods Based on Library Loan Records and Bibliographic Information AbstractWe propose a method to recommend books through machine learning modules based on several featuresincluding library loan recordsWe evaluated the most effective method among ones usingaa Support Vector MachineSVMbRandom Forest andcAdaboostas well as the most effective combination of relevant features among1library loan records2book titles3Nippon Decimal Classification categories4publication year and5frequencies at which books were borrowedWe performed an experiment involving 40 subjects who are students at T UniversityThe books that our methods recommended and the loan records that we used were obtained from the T University LibraryThe results show that books recommended by the SVM based on features123and5were rated most favorably by the subjectsOur method outperforms preceding onessuch as the method proposed by Tsuji et al2013and is comparable in performance to the recommendation by the website AmazoncojpLibrary Automation and Retrieval and IndexingRecommend books automatically with machine learning methodsand index and retrieval based on specific featuresRecommend books with a variety of machine learning methodsespecially based on a variety of characteristicssuch as library borrowing records and other related characteristics