Open AccessImplementation of the Neural Network (NN) Algorithm in Analysis of Student Class Increment Data Based on Report Card Value
Author(s) -
Alimuddin Alimuddin,
Muhammad Saiful
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1539/1/012034
Subject(s) - attendance , class (philosophy) , artificial neural network , mathematics education , computer science , field (mathematics) , operator (biology) , value (mathematics) , test (biology) , process (computing) , report card , settlement (finance) , character (mathematics) , relation (database) , test data , artificial intelligence , machine learning , data mining , psychology , mathematics , software engineering , pedagogy , world wide web , payment , repressor , economic growth , chemistry , biology , operating system , paleontology , biochemistry , geometry , transcription factor , pure mathematics , economics , gene
Formal education is education in schools that takes place regularly and gradually follows clear and strict conditions, the purpose of which is to add insight or knowledge in a person and enrich character, and prepare someone to be able and skilled in a particular field. 12 years formal education that must be obtained by everyone starting from elementary, middle and middle school, in general in the process of class improvement, several stages must be passed by students to be able to proceed to higher grade levels, including good behavior, level attendance of at least 70% and the value must be above the KKM (Minimum Settlement Criteria). KKM is the level of achievement of basic competencies that must be achieved by students. So that in the analysis of determining student achievement classes, data mining techniques are used by applying the Neural Network (NN) algorithm to facilitate the parties involved in analyzing the level of increase in student class and can find out the results of how high the accuracy of the algorithm applied. In this experiment, testing was carried out 3 times with different K-Fold Validations on the cross-validation operator. K-Fold Validation functions to divide the amount of training data and test the data on the tested data, the result of the accuracy that has been tested is 99.26%.