Salsabella, Beatrik Selvidie (2023) Peramalan Penjualan Pakaian Anak-Anak Melalui E-Commerce Didasarkan Pada Jumlah Produksi Di Toko XYZ Menggunakan Arima Box Jenkins Dan Radial Basis Function Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.
Text
10611910000054_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (1MB) | Request a copy |
Abstract
Perkembangan tekonologi berdampak pada meningkatnya daya saing di bidang industri tekstil dan pakaian di seluruh dunia khususnya di Indonesia. Saat ini fashion trend bagi anak-anak juga sudah mulai berkembang dan dipengaruhi oleh banyak hal terutama pada perkembangan teknologi. Perubahan yang pesat pada teknologi informasi tersebut mendominasi seluruh kegiatan sehingga memberikan kemajuan disegala bidang tidak terkecuali e-commerce yang menyebabkan sistem penjualan berevolusi dari konvensional menjadi digital. Ada beberapa masalah yang timbul ketika menjalankan bisnis melalui e-commerce salah satunya adalah permintaan pasar yang sering berubah sehingga menyebabkan jumlah produksi overload atau bahkan kekurangan. Untuk mengatasi permasalahan jumlah produksi maka dilakukan perencanaan produksi. Perencanaan produksi diharapkan mampu memenuhi permintaan konsumen di masa yang akan datang, untuk itu diperlukan ramalan produksi berdasarkan data-data pada periode sebelumnya. Peramalan merupakan langkah awal dari perencanaan produksi. Salah satu metode peramalan yang bisa digunakan adalah ARIMA Box-Jenkins dan Radial Basis Function Neural Network (RBFNN). Dalam penelitian ini dilakukan analisis peramalan penjualan pakaian anak-anak melalui e-commerce yang didasarkan pada jumlah produksi di Toko XYZ. Pada penelitian ini didapatkan bahwa model ARIMA terbaik adalah ARIMA (2,0,0) dengan nilai RMSE sebesar 582,140, MAD sebesar 435,330, dan MAPE sebesar 91,352. Model ARIMA yang diperoleh dibandingkan dengan model RBFNN dengan nilai RMSE sebesar 370,730, MAD sebesar 284,569, dan MAPE sebesar 77,529. Berdasarkan hasil tersebut didapatkan bahwa model RBFNN memiliki nilai akurasi kebaikan model yang lebih kecil dari model ARIMA. Sehingga mampu menghasilkan ramalan jumlah produksi pakaian anak-anak di Toko XYZ yang lebih baik.
================================================================================================================================
The development of technology has a significant impact on competitiveness in the textile and clothing industry worldwide, especially in Indonesia. Currently, fashion trends for children have also begun to develop and are influenced by many things, especially technological developments. The rapid changes in information technology dominate all activities to improve progress in all fields, including e-commerce which has caused the sales system to evolve from conventional to digital. Several problems arise when running a business through e-commerce; one of them is that market demand often changes, causing production amounts to overload or even shortages. Production planning is needed to overcome the problem of the amount of production. Production planning is expected to be able to meet consumer demand in the future; for this reason, a production forecast based on data from the previous period is needed. Forecasting is the first step of production planning. One of the forecasting methods that can be used is ARIMA Box-Jenkins and Radial Basis Function Neural Network (RBFNN). In this study, an analysis of forecasting the sale of children's clothing through e-commerce was carried out, which was based on the amount of production in the XYZ Store. This study found that the best ARIMA model was ARIMA (2,0,0), with an RMSE value of 582,140, MAD of 435,330, and MAPE of 91,352. The ARIMA model was compared with the RBFNN model with RMSE values of 370,730, MAD of 284,569, and MAPE of 77,529. Based on these results, it was found that the RBFNN model has a better accuracy value than the ARIMA model. RBFNN can better forecast the number of children's clothing products in the XYZ Store.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | ARIMA, Clothes, E-commerce, Production, RBFNN, Technology, Pakaian, Produksi, Teknologi |
Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis |
Divisions: | Faculty of Vocational > 49501-Business Statistics |
Depositing User: | Beatrik Selvidie Salsabella |
Date Deposited: | 23 Jun 2023 08:29 |
Last Modified: | 23 Jun 2023 08:29 |
URI: | http://repository.its.ac.id/id/eprint/98215 |
Actions (login required)
View Item |