Pengembangan Algoritma Unsupervised Learning Technique Pada Big Data Analysis di Media Sosial sebagai media promosi Online Bagi Masyarakat
DOI:
https://doi.org/10.15408/jti.v12i1.11342Keywords:
Big Data, Machine Learning, Unsupervised Learning, K-Means DSS (Decion Support System)Abstract
ABSTRAK
Kumpulan data yang besar atau dikenal dengan istilah big data dapat dianalisis dengan berbagai macam teknik. Salah satu teknik untuk mengolah big data adalah Unsupervised Technique. Ada berbagai macam algoritma yang menerapkan teknik ini. Setiap algoritma memiliki cara dan karakteristik masing-masing. Penelitian ini berfokus pada pengembagan algoritma yang menerapkan unsupervised learning technique salah satunya algoritma K-Means dengan mengambil sample data pada masyarakat yang melakukan usaha kreatif dan mandiri. Masyarakat dalam yang memanfaatkan usaha online dan offline dalam pemasarannya. Peneliti melakukan uji eksperimen dan simulasi terhadap algoritma tersebut dengan menghasilkan output berupa aplikasi software serta tabel dan grafik yang mampu menggabungkan data yang didapat dari media social dan kuesioner secara ofline. Hasil analisa pengolahan Data tersebut dapat di gunakan sebagao DSS (Decicion Support System) oleh masyarakat dalam mengambil keputusan pengembangan pemasaran produksinya selanjutnya.
ABSTRACT
Large data collection or known as big data can be analyzed with various techniques. One technique for processing big data is Unsupervised Technique. There are various kinds of algorithms that apply this technique. Each algorithm has its own ways and characteristics. This study focuses on developing an algorithm that implements an unsupervised learning technique, one of which is the K-Means algorithm by taking data samples to people who are doing creative and independent efforts. The Society utilized online and offline business in marketing. The researcher conducted an experimental test and simulation of the algorithm by producing output in the form of software applications as well as tables and graphs that were able to combine data obtained from social media and questionnaires fromline. The results of the analysis of data processing can be used as a DSS (Decion Support System) by the community in making their next production marketing development decisions.
References
Brownlee, Jason. 2016. Supervised and Unsupervised Machine Learning Algorithm. https://machinelearningmastery.com/supervised-and-unsupervised-machine-learning-algorithms/ (diakses 1 November 2017)
Hurwitz, Judith., Et. al. 2013. Big Data for Dummies. New Jersey: John Wiley & Sons, Inc.
Metisen, Melpa. Latipa, Herlina. 2015. Analisis Clustering Menggunakan Metode K-Means dalam Pengelompokkan Penjualan produk pada Swalayan Fadhila. Jurnal media Infotama, Vol 11. No. 2.
Wijaya, Arim. 2010. Analisis Algoritma K-Means untuk Sistem Pendukung Keputusan Penjurusan Siswa di MAN Binong Subang. Skripsi. Bandung: Universitas Komputer Indonesia.
Apriyanti, Nur Ridha., Nugroho, Radityo Adi., Soesanto, Oni. 2015. Algoritma K-Means Clustering dalam Pengolahan Citra Digital Landsat. Kalimantan: Universitas Lambung Mangkurat.
Simon Hudson, Li Huang, Martin S. Roth, Thomas J. Madden. 2015. The influence of social media interactions on consumer–brand relationships: A three-country study of brand perceptions and marketing behaviors. ScienceDirect Intern. J. of Research
Hartati, Sri dan Adi Nugroho. 2012. MongoDB: Implementasi VLDB (Very Large Database) Untuk Sistem Basis Data Tersebar (Distributed Database). Jurnal Teknik Informatika.
Bacquet, Carlos; Gumus, Kubra; Tizer, Dogukan; Zincir-Heywood, A. Nur, and Heywood, Malcolm I. 2009. A Comparison of Unsupervised Learning Techniques for Encrypted Traffic Identification. Dalhousie University.
Anonim. 2016. Netbeans IDE 8.2 Information. https://netbeans.org/community/releases/82/, (diakses 3 Juli 2017)
Aryan, P. 2010. Algoritma K-Means Clustering. http://pebbie.wordpress.com/2008/11/13/algoritma-kmeansclustering.Html. Diakses 1 November 2017.
MacQueen, J. B. 1967. Some Methods for classification and Analysis of Multivariate Observations, Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability. University of California Press.
C. Bacquet, A.N. Zincir-Heywood, and M.I. Heywood. Sep 2009. An Investigation of Multiobjective Genetic algorithms for Encrypted Traffic Identification. In Computational Intelligence in Security for Information Systems: Cisis’ 09, 2nd International Workshop Burgos, Spain, pages 93–100. Springer.
Jordan, M. I. and Mitchel, T. M. 2015. Machine Learning: Trends, Perspectives, and Prospects. American Association for the Advancement of Science.
