Improving Student Enrollment Prediction Using Ensemble Classifiers

Abstract

Abstract:In the recent years, data mining has been utilized in education settings for extracting and manipulating data, and for establishing patterns in order to produce useful information for decision making. There is a growing need for higher education institutions to be more informed and knowledgeable about their students, and for them to understand some of the reasons behind students' choice to enroll and pursue careers. One of the ways in which this can be done is for such institutions to obtain information and knowledge about their students by mining, processing and analyzing the data they accumulate about them. In this paper, we propose a general framework for mining student data enrolled in Science, Technology, Engineering and Mathematics (STEM) using performance weighted ensemble classifiers. We train an ensemble of classification models from enrollment data streams to improve the quality of student data by eliminating noisy instances, and hence improving predictive accuracy. We empirically compare our technique with single model based techniques and show that using ensemble models not only gives better predictive accuracies on student enrollment in STEM, but also provides better rules for understanding the factors that influence student enrollment in STEM disciplines.

Komparasi Model Prediksi Daftar Ulang Calon Mahasiswa Baru Menggunakan Metode Decision Tree Dan Adaboost

“…Baik untuk kepentingan knowledge discovery maupun klasifikasi. Data yang bisa dimanfaatkan untuk proses klasifikasi diambil dari data orang tua mahasiswa, data diri mahasiswa, data demografis, dan riwayat pendidikan [4]. Klasifikasi dapat dilakukan dengan banyak metode namun metode yang umum digunakan pada Educational Data Mining (EDM) adalah Decision Tree [19].…”

“…Tabel V menunjukkan perbandingan jumlah data yang timpang atau tidak seimbang (imbalance) antara yang tidak melanjutkan daftar ulang dan yang melanjutkan daftar ulang setelah diolah. Meskipun ada sedikitnya 3 referensi penelitian terdahulu [2] [9][10] yang menggunakan jenis kelamin dan pekerjaan orang tua sebagai atribut terpilih, penelitian ini menyatakan jika variabel jenis_kelamin dan pekerjaan_orang_tua tidak ada hubungannya dengan penerimaan mahasiswa baru karena nilai p lebih besar dari nilai a. Hasil ini berbeda dengan penelitian [2] yang menjelaskan jika terdapat hubungan antara variabel pekerjaan orang tua dengan penerimaan mahasiswa baru. Untuk memastikan signifikansi hubungan dari kedua atribut tersebut, maka ditambahkan beberapa skenario pelatihan dengan dan tanpa atribut jenis_kelamin maupun pekerjaan_orang_tua.…”

Registration Status Prediction of Students using Machine Learning in the Context of Private University of Bangladesh

“…The results showed that the reasons for individuals drop out in this regard are diverse and unique. Wanjau et al [12], proposed a general framework for mining student data enrolled in Science, Technology, Engineering and Mathematics (STEM) using performance weighted ensemble classifiers. They compared their technique with single model-based techniques and determined that it not only gives better accuracies in the abovementioned context but also more useful for understanding the several factors that influence the enrollment of the student in STEM.…”

Research on machine learning strategy based on voting model

“…Wanjau et al proposed a common system for mining freshmen information enlisted in Science, Innovation, Building, and Science (STEM) utilizing performance-weighted outfit classifiers 2 . The result appears that utilizing outfit models not as it gave way better prescient exactnesses on understudy enrollment in STEM but moreover gives way better rules for understanding the components that impact understudy enrollment in STEM disciplines.…”