., Helda (2024) Pengembangan Model Supply Chain Analytics Untuk Perumusan Kebijakan Pengelolaan Persediaan Produk Dan Bahan Baku Pada Industri Fashion Muslimah. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5010201040-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5010201040-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (4MB) | Request a copy |
|
Text
5010201040-Undergraduate Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (4MB) | Request a copy |
Abstract
Penelitian ini bertujuan mengembangkan model supply chain analytics untuk merumuskan kebijakan dalam penentuan variasi produk (warna, model, fabric) dan pengelolaan persediaan bahan baku pada industri retail fashion muslimah. Dengan customer behavior yang beragam, termasuk preferensi yang bervariasi terhadap warna dan model, perusahaan dihadapkan pada tantangan tingginya ketidakstabilan permintaan dan kompleksitas dalam manajemen inventaris. Di samping itu, tingkat ketidakpastian dalam penyediaan bahan baku juga menjadi tantangan signifikan yang mempengaruhi stabilitas produksi dan ketersediaan produk di pasaran. Fokus utama penelitian ini adalah meningkatkan responsivitas perusahaan terhadap perubahan pasar, meminimalkan biaya operasional yang tinggi, dan mengoptimalkan rantai pasokan. Model supply chain analytics yang dikembangkan bertujuan untuk mengatasi ketidakstabilan demand baik dari variasi maupun quantity menggunakan pendekatan descriptive analytics dan predictive analytics. Tahap pengembangan model supply chain analytics meliputi pembersihan data, analisis data eksploratif, transformasi data, pengembangan model deskriptif dan prediktif, serta pembuatan dashboard interaktif. Pengembangan model deskriptif dilakukan menggunakan teknik visualisasi seperti pie chart, bar chart dan jenis visualisasi data lainnya untuk memahami customer behavior dengan lebih baik. Sementara itu, model prediktif dikembangkan menggunakan algoritma machine learning yaitu Extreme Gradient Boosting yang mencapai akurasi 0,821 untuk melakukan peramalan dengan tingkat ketepatan yang tinggi. Hasil forecasting tersebut digunakan sebagai dasar untuk merumuskan kebijakan manajemen persediaan bahan baku menggunakan metode EOQ (Economic Order Quantity). Untuk meningkatkan aksesibilitas dan efektivitas, model supply chain diintegrasikan ke dalam sebuah dashboard interaktif. Dashboard tersebut tidak hanya mempermudah penggunaan model, tetapi juga memungkinkan adaptasi data secara fleksibel. Dengan pendekatan ini, tidak hanya meningkatkan efisiensi operasional, tetapi juga mendukung pengambilan keputusan yang lebih akurat berdasarkan data terbaru dan pemahaman yang lebih dalam mengenai perilaku konsumen
=====================================================================================================================================
This research aims to develop a supply chain analytics model to formulate policies in determining product variations (color, model, fabric) and managing Raw material inventory in the Muslim fashion retail industry. With diverse customer behavior, including varying preferences for colors and models, companies are faced with the challenge of high demand instability and complexity in inventory management. In addition, the level of uncertainty in the supply of Raw materials is also a significant challenge that affects production stability and product availability in the market. The main focus of this research is to improve the company's responsiveness to market changes, minimize high operational costs, and optimize the supply chain. The developed supply chain analytics model aims to overcome demand instability both in terms of variety and quantity using descriptive analytics and predictive analytics approaches. The development stage of the supply chain analytics model includes data cleaning, exploratory data analysis, data transformation, descriptive and predictive model development, and interactive dashboard creation. Descriptive model development is done using visualization techniques such as pie charts, bar charts and other types of data visualization to better understand customer behavior. Meanwhile, the predictive model was developed using a machine learning algorithm, Extreme Gradient Boosting, which achieved an accuracy of 0.77 to perform forecasting with a high level of accuracy. The forecasting results are used as the basis for formulating Raw material inventory management policies using the EOQ (Economic Order Quantity) method. To increase accessibility and effectiveness, this supply chain model is integrated into an interactive dashboard. The dashboard not only makes it easier to use the model, but also allows flexible adaptation of data. With this approach, it not only improves operational efficiency, but also supports more accurate decision-making based on the latest data and a deeper understanding of consumer behavior.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Supply Chain Analytics, Descriptive Analytics, Predictive Analytics, Machine Learning, Extreme Gradient Boosting, Customer Behavior |
| Subjects: | T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T58.6 Management information systems T Technology > T Technology (General) > T58.8 Productivity. Efficiency T Technology > TS Manufactures > TS155 Production control. Production planning. Production management T Technology > TS Manufactures > TS161 Materials management. |
| Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26201-(S1) Undergraduate Thesis |
| Depositing User: | Helda . |
| Date Deposited: | 02 Aug 2024 04:03 |
| Last Modified: | 07 Aug 2024 02:59 |
| URI: | http://repository.its.ac.id/id/eprint/109735 |
Actions (login required)
 |
View Item |