On the Comparison of Deep Learning Neural Network and Binary Logistic Regression for Classifying the Acceptance Status of Bidikmisi Scholarship Applicants in East Java

Nita Cahyani, Kartika Fithriasari, Irhamah Irhamah, Nur Iriawan

Abstract


Neural Network and Binary Logistic Regression are modern and classical data mining analysis tools that can be used to classify data on Bidikmisi scholarship acceptance in East Java Province, Indonesia. One form of Neural Network model available for various applications is the Resilient Backpropagation Neural Network (Resilient BPNN). This study aims to compare the performance of the Resilient BPNN method as a Deep Learning Neural Network and Binary Logistic Regression method in determining the classification of Bidikmisi scholarship acceptance in East Java Province. After preprocessing data and dividing them into two parts, i.e. sets of testing and training data, with 10-foldcross-validation procedure, the Resilient BPNN and Binary Logistic Regression methods are implemented. The result shows that Resilient BPNN with two hidden layers is the best platformnetwork model. The classificationG-mean resulted by these both methods is that Resilient BPNN with two hidden layers is more representative with better performance than Binary Logistic Regression. The Resilient BPNN is recommended to be used to
predict acceptance of Bidikmisi applicants yearly.


Full Text:

PDF


DOI: https://doi.org/10.11113/matematika.v34.n3.1141

Refbacks

  • There are currently no refbacks.


UTM Logo

Copyright © 2016 Penerbit UTM Press, Universiti Teknologi Malaysia

Disclaimer: This website has been updated to the best of our knowledge to be accurate. However, Universiti Teknologi Malaysia shall not be liable for any loss or damage caused by the usage of any information obtained from this web site.

Best viewed: Mozilla Firefox 4.0 & Google Chrome at 1024 × 768 resolution.