Abstract：Toward Effective Planning and Management Using Predictive Analytics Based on Rental Book Data of Academic Libraries Large scale data and predictive analytics are the most challenging tasks in the field of academic data miningAcademic libraries are a great source of information and knowledge to provide a wide range of services to meet end-user requirementsDue to the rapid changes in the educational environment and availability of huge library rental book datait is required to utilize data mining and machine learning techniques in the context of the academic library to extract and analyze underlying knowledge from rental book datawhich is important to facilitate library administration to drive better future decisions to improve and manage library resources effectivelyThese are the following resourcessuch as managing future demands of the library booksselection and arrangement of the booksoperational efficiencyand also improve the quality of interaction between the library and end-usersetcThis work uses and analyzes a real dataset collected from the library of Jeju National Universitythe Republic of KoreaThe dataset contains 2211413 rental book records including 173671 unique book records57203 unique number of the rental userand 78 data parametersIn this paperwe propose a novel model to analyze and predict library rental book data to facilitates library administration in order to plan and manage library resources effectively and provide better services to end-usersThe proposed model consists of two different moduleslibrary data analysis and prediction modulesFirstlywe use data mining techniques to analyze and extract useful underlying patterns from library rental book datawhich can lead to plan and manage library resources effectivelySecondlya novel prediction model is proposed based on Deep Neural NetworkDNNSupport Vector RegressorSVRand Random ForestRFto predict future usage of the academic libraries rental booksThe performance results of the implemented regression models are evaluated in terms of MAEMSEand RMSEIn this paperit is found that the DNN model performs significantly better than SVR and RFThe experimentation results show that the proposed model improves the future usage of library books to facilitate library administration to plan and manage library resources effectivelyBased on the proposed model resultsthe academic library administration can easily plan and manage resources effectively to provide quality services to end-users Library AutomationUse data exploration and machine learning methods to automatically analyze and predict borrowing dataCollection classificationUsing the results of analysis can help the selection and arrangement of booksRetrieval and IndexingBy predicting future usageit will help improve the efficiency of retrieval and indexingThis research uses data exploration technology to analyze and extract useful potential models from the librarys borrowing datawhich helps the library to effectively plan and manage resourcesIn additionthe study also proposed a new predictive model based on deep neural networkDNNsupport vector regressionSVRand random forestRFto predict the future use of the academic library