Prediksi Penjualan Strapping Band Pada PT. Powerpack Industrial Solution Menggunakan Optimasi Grid Search Pada Model XGBoost.

Balqhis, Amira (2025) Prediksi Penjualan Strapping Band Pada PT. Powerpack Industrial Solution Menggunakan Optimasi Grid Search Pada Model XGBoost. Undergraduate thesis, UPN VeteranJawa Timur.

	Text 21083010091_Cover.pdf Download (924kB)
	Text (Bab 1) 21083010091_Bab 1.pdf Download (258kB)
	Text (Bab 2) 21083010091_Bab 2.pdf Restricted to Registered users only until 18 June 2028. Download (819kB)
	Text (Bab 3) 21083010091_Bab 3.pdf Restricted to Registered users only until 18 June 2028. Download (387kB)
	Text (Bab 4) 21083010091_Bab 4.pdf Restricted to Registered users only until 18 June 2028. Download (1MB)
	Text (Bab 5) 21083010091_Bab 5.pdf Download (248kB)
	Text (Daftar Pustaka) 21083010091_Daftar Pustaka.pdf Download (189kB)
	Text (Lampiran) 21083010091_Lampiran.pdf Restricted to Registered users only until 18 June 2028. Download (354kB)

Abstract

PT. Powerpack Industrial Solution, operating in the field of industrial solutions supply, particularly strapping band products, faces challenges in predicting fluctuating sales, which can lead to overstock or stockout conditions, resulting in increased operational costs and decreased customer satisfaction. The main problem addressed is the inaccuracy in forecasting strapping band demand due to high market fluctuations and the complexity of historical sales data. To overcome this issue, this study proposes the use of an Extreme Gradient Boosting (XGBoost) model optimized through Grid Search technique to improve sales prediction accuracy. The method involves applying the XGBoost model combined with systematic hyperparameter tuning using Grid Search, based on sales data consisting of dates, product types, and quantities sold. Model evaluation is conducted using the Mean Absolute Percentage Error (MAPE) metric to assess prediction accuracy. The urgency of this research lies in the critical need for accurate demand forecasting to optimize inventory management, thus minimizing the risk of overstock and stockout while enhancing operational efficiency. The innovation introduced in this study is the application of Grid Search optimization to the XGBoost model in the context of strapping band sales prediction, a topic that has been scarcely explored in the packaging and distribution industry. This research addresses a gap in the literature by providing a more efficient, data-driven solution for inventory management in manufacturing and distribution companies. The results show that after optimization, the XGBoost model successfully reduced the MAPE from 9.59% to 7.12%, leading to improved prediction accuracy and more effective stock management for the company. Keywords: : Grid Search, Overstock, Stockout, Strapping Band, Xgboost Model

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@upnjatim.ac.id
Thesis advisor	Damaliana, Aviolla Terza	NIDN0002089402	aviolla.terza.sada@upnjatim.ac.id

Subjects:

Q Science > Q Science (General)
Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TA Engineering (General). Civil engineering (General)

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Amira Amira Balqhis

Date Deposited:

19 Jun 2025 02:06

Last Modified:

19 Jun 2025 02:06

URI:

https://repository.upnjatim.ac.id/id/eprint/38490