The K-Nearest Neighbor Algorithm using Forward Selection and Backward Elimination in Predicting the Student’s Satisfaction Level of University Ichsan Gorontalo toward Online Lectures during the COVID-19 Pandemic

Academic services are actions taken by state and private universities to provide convenience for student’s academic activities. During the current covid-19 pandemic, every university remains active in This study aimed apply K-Nearest Neighbor algorithm predicting level of student satisfaction with online lectures at University Ichsan Gorontalo. Our main aim was obtain quantitative information measure during which should be into account when making decisions. is a non-parametric Algorithm that can used classification regression, but better if feature selection applied selecting features not relevant model. Feature Selection this research Forward Backward Elimination. Seeing results experiments have been carried out application K-nearest feature, forecasting consideration or policy decision making. The highest accuracy model an rate 98.00%. Thus, experimental showed selection, namely forward variables compared backward elimination.