PREDIKSI PENJUALAN POCO X6 PRO BLACK MENGGUNAKAN SUPPORT VECTOR REGRESSION DENGAN ALGORITMA GRIDSEARCH DI E-COMMERCE XYZ

Anisa Budiarti, . (2025) PREDIKSI PENJUALAN POCO X6 PRO BLACK MENGGUNAKAN SUPPORT VECTOR REGRESSION DENGAN ALGORITMA GRIDSEARCH DI E-COMMERCE XYZ. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf

Download (242kB)
[img] Text
AWAL.pdf

Download (1MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only

Download (464kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only

Download (544kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only

Download (543kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only

Download (1MB)
[img] Text
BAB 5.pdf

Download (335kB)
[img] Text
DAFTAR PUSTAKA.pdf

Download (253kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only

Download (175kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only

Download (3MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only

Download (15MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only

Download (866kB)

Abstract

PT XYZ, an e-commerce company, faces the challenge of anticipating the fluctuating demand pattern for the Poco X6 Pro Black smartphone. This fluctuation is influenced by promotional periods, market trends, and the launch of new series, all of which often affect the weekly sales volume. This study aims to map the demand fluctuation pattern, determine the best kernel and parameters for the prediction model using the Support Vector Regression (SVR) method with the Grid Search algorithm, and build a forecasting model with a low error rate. The results show that the SVR model with a polynomial kernel, a cost (C) parameter of 1000, epsilon of 0.5, degree of 2, and gamma scale of 1.5, combined with a 60:40 data split ratio, is the best combination with a MAPE of 14.16% and an R² of 0.798. The model’s validity was tested through a sensitivity analysis using three scenarios: baseline, sales spike due to promotions, and post-promotion decline. The test results demonstrate that the model can adapt to changes in sales conditions. These findings support PT XYZ in preparing more accurate inventory planning to meet customer demand.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110312038] [Pembimbing: Siti Rohana Nasution] [Penguji 1: Donny Montreano] [Penguji 2: Santika Sari]
Uncontrolled Keywords: Support Vector Regression, Sales Forecasting, E-commerce, Demand Fluctuation
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
Divisions: Fakultas Teknik > Program Studi Teknik Industri (S1)
Depositing User: ANISA BUDIARTI
Date Deposited: 01 Aug 2025 06:26
Last Modified: 01 Aug 2025 06:26
URI: http://repository.upnvj.ac.id/id/eprint/39011

Actions (login required)

View Item View Item