ICT and Mobile Technology Features Predicting the University of Indian and Hungarian Student for the Real-Time

摘要

Feature extraction has a vibrant part in Machine learning (ML) to identify the data patterns with optimum accuracy. We proposed some significant features to predict the student's institution or university based on their answers in the technological survey. Four experiments were performed in IBM SPSS Modeler version 18.2 using 4 ML to resolve the binary classification problem. In the university prediction problem., the uppermost accuracy of 94.26% is provided by eXtreme Gradient Boosting Tree (XGBT) and suggested 18 significant features out of a total of 37. Further., the Artificial Neural Network (ANN) with boosting scored second maximum accuracy of 93.96% and recommended 10 significant features; Support Vector Machine (SVM) provided third-highest accuracy of 92.45% with the recommendation of 12 features; and Random Tree (RT) attained the least accuracy 92.15% with recommendation of 10 important features. The findings of the paper conclude that the XGBT classifier outperformed others in prediction. Also., a noteworthy dissimilarity was found between XGBT's accuracy and SVM's accuracy., RT's accuracy.