Prediction of Skincare Sales Turnover Using the Support Vector Method at the Widya Msglow Sidoarjo Company
Bilah Samping Artikel
Isi Artikel Utama
Abstrak
Every entrepreneur will certainly follow technological developments in the business world. MsGlow is one of the
skincare businesses. The skincare business is one of the businesses that must compete with rapid and complex
changes, and this very competitive makes business people have to think of strategies for business continuity in order to compete and also survive. One way that can be done is to utilize existing sales data. The importance of fast and
precise operational data processing, information system facilities can be an alternative to solving problems in data
processing, minimizing errors and accelerating the data processing process. As the number of sales transactions
increases, there will be a buildup of data that has not been processed optimally. With the above problems, a
forecasting system was created that can forecast skincare sales turnover using the Support Vector Machine (SVM)
method. In this study, turnover in several areas will be forecasted. The kernel function variations used in Support
Vector Machine (SVM) are RBF, Linear, and, Polynomial Degree 2. The results obtained from this research trial
show that the overall forecasting model is good. The accuracy of the three areas obtained with the RBF kernel has a
relatively good MAPE. In the accuracy test to predict skincare sales turnover, the three areas got a fairly good
accuracy value of 94.46%. In the Sidoarjo area, it is predicted that there will be a lot of decrease in turnover in 2023-
2024.
Rincian Artikel
Artikel ini berlisensi Creative Commons Attribution 4.0 International License.
Referensi
U. Amelia, J. Indra, A.F.N. Masruriyah, (2022). Implementasi Algoritma Support Vector Machine (SVM) untuk Prediksi Penyakit Stroke dengan Atribut Berpengaruh, Scientific Student Journal for Information, Technology and Science, vol. 3, no. 2, pp.254–259.
A.S. Batubara, (2020). Analisa Prediksi Penjualan Jersey World Cup 2018 Terlaris dengan Menggunakan Metode Support Vector Machine (Studi Kasus: Toko One Sport Football Distro), Journal of Information System Research (JOSH), vol. 1, no. 4, pp.246-257.
A. Darmawan, N. Kustian, and W. Rahayu, (2018). Implementasi Data Mining Menggunakan Model SVM untuk Prediksi Kepuasan Pengunjung Taman Tabebuya, STRING (Satuan Tulisan Riset dan Inovasi Teknologi), vol. 2, no. 3, pp.299-307. https://doi.org/10.30998/string.v2i3.2439. DOI: https://doi.org/10.30998/string.v2i3.2439
I. Fitriyaningsih, and Y. Basani, (2019). Flood Prediction with Ensemble Machine Learning using BP-NN and SVM. Jurnal Teknologi dan Sistem Komputer, vol. 7, no. 3, pp.93–97. https://doi.org/10.14710/jtsiskom.7.3.2019.93-97 DOI: https://doi.org/10.14710/jtsiskom.7.3.2019.93-97
D.T. Larose, and C.D. Larose, (2014). Discovering Knowledge in Data: An Introduction to Data Mining, John Willey & Sons. DOI: https://doi.org/10.1002/9781118874059
F.R. Lumbanraja, I.H.B. Sitepu, D. Kurniawan, and A. Aristoteles, (2020). Prediksi Jumlah Penderita Penyakit Tuberkulosis Di Kota Bandar Lampung Menggunakan Metode SVM (Support Vector Machine). Klik - Kumpulan Jurnal Ilmu Komputer, vol. 7, no. 3, pp.320-330. https://doi.org/10.20527/klik.v7i3.350 DOI: https://doi.org/10.20527/klik.v7i3.350
M.F. Naufal, (2017). Peramalan Jumlah Wisatawan Mancanegara yang Datang ke Indonesia Berdasarkan Pintu Masuk Menggunakan Metode Support Vector Machine (SVM), Skripsi Sistem Informasi, Institut Teknologi Sepuluh Nopember, Surabaya.
D. Saputra, and M. Ary, (2020). Prediksi Minat Klien pada Produk Deposito Menggunakan Algoritma SVM Parameter Kernel Polynomial. in Proceeding of EProsiding Sistem Informasi (POTENSI), vol. 1, no. 1, pp.162-171.
A.P. Sembiring, and S. Faza, (2021). Prediksi Tingkat Kejahatan Berdasarkan Artikel Berita Menggunakan Metode Support Vector Machine (SVM), In proceeding of Applied Business and Engineering Conference, vol. 9, pp.10–19.
F.R. Setiawan, (2018). Prediksi Pergerakan Harga Saham dengan Metode Support Vector Machine (SVM) Menggunakan Trend Deterministic Data Preparation Program Studi Sarjana Ilmu Komputasi Fakultas Informatika Universitas Telkom Bandung. In proceeding of e-Proceeding of Engineering, vol. 5, no. 3, pp.8356-8372.
V.N. Vapnik, (1999).The Nature of Statistical Learning Theory 2nd edition, Springer-Verlag, New York Berlin Heidelberg.
H.S.W. Hovi, A.I. Hadiana, F.R. Umbara, (2022). Prediksi Penyakit Diabetes Menggunakan Algoritma Support Vector Machine (SVM), Informatics and Digital Expert (INDEX), vol. 4, no. 1, pp.40–45. https://doi.org/10.36423/index.v4i1.895 DOI: https://doi.org/10.36423/index.v4i1.895