Development of New Hybrid Admission Decision Prediction Models Using Support Vector Machines Combined with Feature Selection

Abstract

The purpose of this paper is to develop new hybrid admission decision prediction models by using Support Vector Machines (SVM) combined with a feature selection algorithm to investigate the effect of the predictor variables on the admission decision of a candidate to the School of of Physical Education and Sports at Cukurova University. Experiments have been conducted on the dataset, which contains data of participants who applied to the School in 2006. The dataset has been randomly split into training and test sets using 10-fold cross validation as well as different percentage ratios. The performance of the prediction models for the datasets has been assessed using classification accuracy, specificity, sensitivity, positive predictive value (PPV) and negative predictive value (NPV). The results show that a decrease in the number of predictor variables in the prediction models usually leads to a parallel decrease in classification accuracy.Keywords: machine learning; prediction; physical ability test; feature selection;

Enhancing the Efficiency of Diabetes Prediction through Training and Classification using PCA and LR Model

“…Features Used ML Algorithms Accuracy [4] Hybrid feature selection strategy using SVM Not specified SVM Up to 85% [5] SVM and Random Forest models Not specified SVM, Random Forest Up to 85% [6] Deep learning method using CNN Not specified CNN Up to 88% [7] ML-based strategy using genetic and clinical data Genetic and clinical data…”

“…Several research studies have been conducted to enhance computational efficiency in diabetes prediction through training and classification using ML classifiers. For instance, in a study by [4], the authors developed a hybrid feature selection strategy for diabetes prediction using support vector machines (SVM), while in a similar vein, [5] employed SVM and random forest models for diabetes prediction, achieving an accuracy of up to 85%.…”

“…The LR model is defined as: (5) This can be done using optimization algorithms such as gradient descent or Newton's method. 4. Use the fitted model to predict the probability of the outcome being 1 for each observation in the testing set: Let X test std be the standardized version of X test .…”

Untitled

“…A participant's admission decision is related with the participant's total scores from the physical ability test (PATS) together with his/her scores from National Student Selection Exam (NSSE) and National Student Placement Exam (NSPE), Grade Point Average (GPA) and specialization area at high Ozsert-Yigit, G., Akay, M. F. & Alak, H. (2017). Development of New Hybrid Admission Decision Prediction Models Using Support Vector Machines Combined with Feature Selection.…”

“…-Yigit, G.,Akay, M. F. & Alak, H. (2017). Development of New Hybrid Admission Decision Prediction Models Using Support Vector Machines Combined with Feature Selection.…”