Feature Selection pada Azure Machine Learning untuk Prediksi Calon Mahasiswa Berprestasi
Article Sidebar
Main Article Content
Abstract
Universities can not only depend on digital marketing capabilities that are currently widely used but also utilize emerging technologies such as predictive analytics. This research attempts to make a predictive basis for analytic applications by utilizing Azure Machine Learning. In addition to utilizing machine learning capabilities, the author tries to use Feature Selection which is provided to obtain attributes that support research goals related to the world of education. This research aims to find relevant factors for outstanding student candidates for every student admission process. This research uses the Support Vector Machine Algorithm and comparison of the Feature Selection using Pearson Correlation Coefficient and Mutual Information. The results obtained using 10 attributes obtained the best results of 0.827 for accuracy and 0.831 for precision
Institusi pendidikan tidak boleh hanya bergantung pada kemampuan digital marketing yang saat ini banyak digunakan namun juga memanfaatkan teknologi yang sedang berkembang seperti predictive analytic. Penelitian ini mencoba membuat dasar aplikasi predictive analytic dengan memanfaatkan Azure Machine Learning. Selain memanfaatkan kemampuan machine learning, penulis mencoba menggunakan Feature Selection yang disediakan untuk memperoleh atribut yang mendukung tujuan penelitian terkait dunia pendidikan. Penelitian ini bertujuan menemukan faktor yang relevan untuk calon mahasiswa berprestasi pada setiap penerimaan mahasiswa baru yang dilakukan. Penelitian ini menggunakan Algoritma Support Vector Machine serta perbandingan Feature Selection menggunakan Pearson Correlative Coefficient dan Mutual Information. Hasil yang diperoleh menggunakan 10 atribut memperoleh hasil terbaik 0.827 untuk accuracy dan 0.831 untuk precision.
Article Details
This work is licensed under a TESLA: Jurnal Teknik Elektro Creative Commons Attribution-ShareAlike 4.0 International License. 
References
Lusi Ariyani, 2016, “Kajian Penerapan Model C45, Support Vector Machine (SVM), dan Neural Network dalam Prediksi Kenaikan Kelas”, Faktor Exacta 9(1): 72-86, 2016. ISSN: 1979-276x.
Fahriah, Sirli dan Heru Agus Santoso. Penerapan Algoritma ID3 untuk perediksi Minat Studi Mahasiswa Teknik Informatika Pada Universitas Dian Nuswantoro.
Ahmad, Iftikhar. Basheri, Mohammad and Iqbal, Muhammad Javed. 2018, “Performance Comparison on Support Vector Machine, Random Forest, and Extreme Learning Machine for Intrusion Detection”, IEEE Access Volume 6, 2018.
Li, Jundong and Liu, Huan, 2017, “Challenges of Feature Selection for Big Data Analytics”. IEEE Computer Society, March/April 2017.
Zollanvari, Amin. Kizilirmak, Refik Caglar, Kho, Yau Hee and Torrano, Daniel Hernandez, 2018, “Predicting Students’ GPA and Developing Intervention Strategies Based on Self-Reglatory Learning Behaviors”. IEEE Access, Volume 5, 2017.
Yin, Y., Han, D., & Cai, Z. (2011). Explore Data Classification Algorithm Based on SVM and PSO for Education Decision. Journal of Convergence Information Technology, 6(10), 122–128.
Betha Nurina Sari, 2017, “Prediksi Performa Akademik Siswa Pada Pelajaran Matematika Menggunakan Bayesian Networks dan Algoritma Klasifikasi Machine Learning”, KNPMP II, Universitas Muhammadiyah Surakarta. ISSN: 2502-6526.
http://aryatryasthana.blogspot.com/2015/10/tugas-v-cloud-computing-e-commerce-dan.html diakses pada 28 September 2018.
Sembiring, S., Zarlis, M., Hartama, D., Ramliana, S., & Wani, E. (2011). Prediction of Student Academic Performance By an Application of Data Mining Techniques. International Conference on Management and Artificial Intelligence (IPEDR), 6, 110–114.
Punlumjeak, Wattana. Rachburee, Nachirat and Arunrerk, Jedsada. “Big Data Analytics: Student Performance Prediction Using Feature Selection and Machine Learning on Microsoft Azure Platform”, Journal of Telecommunication, Electronic and Computer Engineering. Vol.9 No.1-4.