Klasifikasi Mutu Pembelajaran Hybrid berdasarkan Algoritma C.45, Random Forest dan Naïve Bayes dengan Optimasi Bootsrap Areggating (Bagging) pada masa COVID-19

Dadang Sudrajat (STMIK IKMI, Cirebon)
Ade Irma Purnamasari (STMIK IKMI, Cirebon)
Arif Rinaldi Dikananda (STMIK IKMI, Cirebon)
Dian Ade Kurnia (STMIK IKMI, Cirebon)
Agus Bahtiar (STMIK IKMI, Cirebon)

JURIKOM (Jurnal Riset Komputer)
Vol 9, No 6 (2022): Desember 2022

This study aims to find the best model from the 3 (three) models chosen, namely Random Forest, Naïve Bayes and C4.5 against the classification of hybrid learning quality held at SMK Cendekia Cirebon City during the COVID-19 period. The research method is carried out by referring to the approach or technique of machine learning with the stages of data collection, data preparation, data transformation, modeling and evaluation.  The final results of this study are measured by the level of accuracy of hybrid learning quality aspects, namely teachers, subject matter, integrity, student motivation, and technology resources with bad, sufficient, good and very good categories.. Based on the experiments that have been carried out, the accuracy results for the Random Forest algorithm were obtained by 93.92%, Naïve Bayes by 93.22% and C4.5 by 77.16%. Thus this study recommends the best classification algorithm model based on dataset processing to measure this hybrid learning quality model is Random Forest