Classification of Student Graduation using Naïve Bayes by Comparing between Random Oversampling and Feature Selections of Information Gain and Forward Selection

Abstract

Class-imbalanced data with high attribute dimensions in datasets frequently contribute to issues in a classification process as this can affect algorithms’ performance in the computing process because there are imbalanced numbers of data in each class and irrelevant attributes that must be processed; therefore, this needs for some techniques to overcome the class-imbalanced data and feature selection to reduce data complexity and irrelevant features. Therefore, this study applied random oversampling (ROs) method to overcome the class-imbalanced data and two feature selections (information gain and forward selection) compared to determine which feature selection is superior, more effective and more appropriate to apply. The results of feature selection then were used to classify the student graduation by creating a classification model of Naïve Bayes algorithm. This study indicated an increase in the average accuracy of the Naïve Bayes method without the ROs preprocessing and the feature selection (81.83%), with the ROs (83.84%), with information gain with 3 selected features (86.03%) and forward selection with 2 selected features (86.42%); consequently, these led to increasing accuracy of 4.2% from no pre-processing to information gain and 4.59% from no pre-processing to forward selection. Therefore, the best feature selection was the forward selection with 2 selected features (GPA of the 8th semester and the overall GPA), and the ROs and both feature selections were proven to improve the performance of the Naïve Bayes method.

Sentiment Classification on Twitter Social Media Using K-Means Clustering, C4.5 and Naive Bayes (Case Study: Blocking Paypal by Kominfo)

“…The Naive Bayes Classifier method is one of the algorithms in classification techniques that use probability and statistics presented by the English scientist Thomas Bayes, which predicts the likelihood of the future based on past experiences, thus known as Bayes' Theorem [5]. Some studies have shown the feasibility of this algorithm in building smart-system, such as the intelligent system for student personality classification [6], the system for NPC braking decisions in a racing game [7], and the new student admission recommendation system [8]. We choose the Naive Bayes algorithm for the machine learning method, using these studies as a reference in building smart security.…”

Predicting Factors that Affect East Asian Students’ Reading Proficiency in PISA

“…In work by [26] multiple linear regression (MLR), multilayer perceptron (MLP) and classification and regression tree (CART) are compared with MLP and CART performing better than MLR. Other than predicting the risk of dropout, there are studies on using machine learning to predict graduation [27], [28][29] has created a mobile application with deep learning to enhance English and Arabic vocabulary among children. The mobile application has recorded more than 90% accuracy for image classification.…”

Feature Minimization for Diabetic Disorders High Performances Prediction System-based on Random Forest Tree

“…At the same time, attribute selectors should be agreed upon and matched to be similar feature determination. It means that when two or more techniques are demonstrated, the attribute names should be similar to other techniques even if one or two attributes are different from other techniques, as suggested in [35], [36], [37], [38], and [39]. Diabetic disease needs a unique study to improve the availability of investigation or reduce the variance and spread of this vital disease.…”