Paper Title : Application Of Data Mining To Predict The Graduation Students With K-Nearest Neighbor Algorithm and Learning vector quantization desktop Based On Study Program Information System Faculty Of Technology BUDI LUHUR UNIVERSITY

ISSN : 2394-2231
Year of Publication : 2021

10.29126/23942231/IJCT-v8i2p45

Authors: Andri Kusuma Wardana, Indra Darmawan, Ardiane Rossi Kurniawan Maranto

         



MLA Style: Andri Kusuma Wardana, Indra Darmawan, Ardiane Rossi Kurniawan Maranto " Application Of Data Mining To Predict The Graduation Students With K-Nearest Neighbor Algorithm and Learning vector quantization desktop Based On Study Program Information System Faculty Of Technology BUDI LUHUR UNIVERSITY " Volume 8 - Issue 2 March-April , 2021 International Journal of Computer Techniques (IJCT) ,ISSN:2394-2231 , www.ijctjournal.org

APA Style: Andri Kusuma Wardana, Indra Darmawan, Ardiane Rossi Kurniawan Maranto " Application Of Data Mining To Predict The Graduation Students With K-Nearest Neighbor Algorithm and Learning vector quantization desktop Based On Study Program Information System Faculty Of Technology BUDI LUHUR UNIVERSITY " Volume 8 - Issue 2 March-April , 2021 International Journal of Computer Techniques (IJCT) ,ISSN:2394-2231 , www.ijctjournal.org

Abstract
Data Mining is an extraction processing technique on the data patternsto manipulate that data becomes more valuable information Data Mining can serve to predict a problem by studying the patterns in large data, one is predicting graduation. As in Budi Luhur University Faculty of Information Technology Studies Program Information System, to improve the quality of education it takes data mining application that the management can determine the prediction of graduation students. By knowing the predictions of graduation, then the management can pay more attention to students who get the prediction does not pass. Thus the faculty to increase the graduation rate to 100%. Data mining applications using K-Nearest Neighbor algorithm and Learning Vector Quantization in the process of classification. Before the prediction process, will be trained on all the datasets samples that have been collected in the form of a list of allstudents in the class HSK 2014 until 2016 to get the patterns of each dataset. This distance will be taken as the K Value begins with the smallest distance, in this case it will use the value K = 55. Of the 55 datasets obtained from KNN process, will be used for classification using Learning Vector Quantization. Learning Vector Quantization classify test data to calculate the distance of the nearest weight training results of each class in the dataset. After the test data has a range of weightsfrom each datasetselection processis carried out within the smallest weight that will determine the classification on the test data based on the value. Applications are able to predict graduation Prodi Faculty of Information Technology Information Systems.

Reference
[1] [1] Dessy, WM & Irawan, A., 2012. Comparison Method of Neural Network. [2] backpropagation and Learning Vector [3] Quantization On Facial Recognition. Journal of Computer and Information Technology, 1 (1), pp.45-51. [2] Hariri, FR, Utami, E. & Amborowati, A., 2015. [4] Learning Vector Quantization for the Classification of Abstract Thesis. CITEC Journal, 2 (2), pp.128-143 [3] Krmac, EV, 2011. [5] Leidiyana, H., 2013. The application of KNearest Neighbor Algorithm For Determining Risk of Motor Vehicle Ownership Loan. [6] Journal of Research in Computer Science, System Embedded & Logic, 1 (1), pp.65-76. [7] Prasetyo, TF, et al., 2016 KNOWLEDGE BASED SYSTEM. National Seminar on Information Technology Application (Insertion), pp.32-37. [6] [8] Ramadan, DNKEM, 2016. Application of Data Mining Algorithm Naïve Bayes Clasifier to Know the Customer's Interests Buy High Car [9] Risman, H., Nugroho, D. & WU, YR, 2013. APPLICATION METHOD K-Nearest Neighbor APPLICATION

Keywords
————Data Mining, K-Nearest Neighbor, Learning Vector Quantization, Artificial Neural Networks.