Optimasi Decision Tree Menggunakan Particle Swarm Optimization Pada Data Siswa Putus Sekolah

Abstract

Education is the right of every citizen, even government makes program to promote the compulsory education of 12 years. Drop out of school has become an obstacle to the government program where the dropout is caused by many factors, including economic factors, geographical conditions, and students' own desires. ID3 is able to generate a decision tree from a very large data set. This decision tree can be used as a reference for possible drop out of students. In order to be a good reference then the resulting classification must have a high accuracy. PSO is known to increase the accuracy of various kinds of data mining classification. ID3 in this study yielded 72.5% accuracy while after optimized with PSO then ID3 will yield 85% accuracy.

Enhancing Special Needs Identification for Children: A Comparative Study on Classification Methods Using ID3 Algorithm and Alternative Approaches

“…Model data mining has been tested for its accuracy using cross-validation, which is a performance evaluation method involving the division of the dataset into segments for training and testing. The 10-fold cross-validation method divides the dataset into 10 equally sized segments, where each segment is used alternately as the testing data in 10 iterations of training and testing processes (Kurniawan & Rosadi, 2017). The testing results can be seen in the image below:…”

Analisis Penerapan Optimasi Perbandingan Kinerja Algoritma C4.5 Dan Naïve Bayes Berbasis Particle Swarm Optimization (Pso) Untuk

“…Salah satu algoritma optimasi yang cukup popular adalah Particle Swarm Optimization (PSO). Particle Swarm Optimization (PSO) telah banyak memecahkan masalah optimasi algoritma [13], [14], [15].…”