Muhyidin, Ahmad (2024) ANALISA DAN IMPLEMENTASI ALGORITMA RANDOM FOREST DAN EXPONENTIAL SMOOTHING DALAM MEMPREDIKSI PERKIRAAN PERMINTAAN PADA MANAJEMEN RANTAI PASOK. S1 thesis, Universitas Mercu Buana - Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (COVER)
41519110200-AHMADMUHYIDIN-01 Cover - Ahmad Muhyidin.pdf Download (614kB) |
|
Text (ABSTRAK)
41519110200-AHMADMUHYIDIN-02 Abstrak - Ahmad Muhyidin.pdf Download (92kB) |
|
Text (BAB I)
41519110200-AHMADMUHYIDIN-03 Bab 1 - Ahmad Muhyidin.pdf Restricted to Registered users only Download (95kB) |
|
Text (BAB II)
41519110200-AHMADMUHYIDIN-04 Bab 2 - Ahmad Muhyidin.pdf Restricted to Registered users only Download (380kB) |
|
Text (BAB III)
41519110200-AHMADMUHYIDIN-05 Bab 3 - Ahmad Muhyidin.pdf Restricted to Registered users only Download (179kB) |
|
Text (BAB IV)
41519110200-AHMADMUHYIDIN-06 Bab 4 - Ahmad Muhyidin.pdf Restricted to Registered users only Download (466kB) |
|
Text (BAB V)
41519110200-AHMADMUHYIDIN-07 Bab 5 - Ahmad Muhyidin.pdf Restricted to Registered users only Download (88kB) |
|
Text (DAFTAR PUSTAKA)
41519110200-AHMADMUHYIDIN-08 Daftar Pustaka - Ahmad Muhyidin.pdf Restricted to Registered users only Download (188kB) |
|
Text (LAMPIRAN)
41519110200-AHMADMUHYIDIN-09 Lampiran - Ahmad Muhyidin.pdf Restricted to Registered users only Download (958kB) |
|
Text (LEMBAR KEABSAHAN)
41519110200-AHMADMUHYIDIN-10 Hasil Scan Formulir Pernyataan Keabsahan dan Persetujuan Publikasi Tugas Akhir - Ahmad Muhyidin.pdf Restricted to Repository staff only Download (100kB) |
Abstract
Manajemen stok yang efektif merupakan tantangan utama dalam rantai pasok, terutama dalam menghadapi ketidakpastian permintaan pasar. Penelitian ini menganalisis dan mengimplementasikan algoritma Random Forest dan Simple Exponential Smoothing untuk memprediksi penjualan dengan tujuan mengoptimalkan permintaan stok di PT Karya Kreasi Nasional, menggunakan data riwayat transaksi penjualan produk. Dari evaluasi model, Simple Exponential Smoothing menunjukkan performa terbaik dengan metrik MAE 11.49, MSE 1361.64, RMSE 36.9, dan MAPE 24.78, dibandingkan dengan Holt Linear Trend (MAE 12.51, MSE 1063.28, RMSE 32.61, MAPE 36.63) dan Holt-Winters Seasonal (MAE 12.51, MSE 997.35, RMSE 31.58, MAPE 45.07). Sementara itu, Random Forest menunjukkan metrik yang kurang optimal (MAE 17.91, MSE 4688.8, RMSE 68.47, MAPE 73.27). Implementasi model dalam sistem manajemen stok perusahaan menggunakan Django REST Framework dan Vue.js telah diuji dengan data baru dan menunjukkan akurasi serta keandalan yang baik. Evaluasi hasil prediksi mingguan dibandingkan dengan penjualan nyata pada minggu pertama Juli 2024 menghasilkan metrik MAE 11.07, MSE 689.41, RMSE 26.26, dan MAPE 53.78. Hasil ini menunjukkan bahwa model prediksi dapat memfasilitasi pengoptimalan persediaan, mengurangi risiko kelebihan dan kekurangan stok, serta meningkatkan efisiensi operasional. Effective stock management is a critical challenge in supply chain management, particularly when addressing market demand uncertainties. This study analyzes and implements Random Forest and Simple Exponential Smoothing algorithms to forecast sales with the objective of optimizing stock demand at PT Karya Kreasi Nasional, utilizing historical sales transaction data. The evaluation results indicate that Simple Exponential Smoothing outperforms other methods, with metrics of MAE 11.49, MSE 1361.64, RMSE 36.9, and MAPE 24.78. In comparison, Holt Linear Trend achieves MAE 12.51, MSE 1063.28, RMSE 32.61, and MAPE 36.63, while Holt-Winters Seasonal records MAE 12.51, MSE 997.35, RMSE 31.58, and MAPE 45.07. Random Forest, on the other hand, demonstrates less favorable metrics with MAE 17.91, MSE 4688.8, RMSE 68.47, and MAPE 73.27. The implementation of the prediction models in the company's stock management system using Django REST Framework and Vue.js was validated with new data, showing satisfactory accuracy and reliability. A comparison of weekly predictions against actual sales for the first week of July 2024 yields metrics of MAE 11.07, MSE 689.41, RMSE 26.26, and MAPE 53.78. These findings suggest that the prediction models can significantly contribute to inventory optimization, mitigate the risks of overstocking and stockouts, and enhance operational efficiency.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41519110200 |
| Uncontrolled Keywords: | Random Forest, Exponential Smoothing, Manajemen Stok, Perkiraan Permintaan,Django REST Framework Random Forest, Exponential Smoothing, Stock Management, Demand Forecast, Django REST Framework |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | SILMI KAFFA MARISKA |
| Date Deposited: | 06 Aug 2024 07:54 |
| Last Modified: | 06 Aug 2024 07:54 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/90047 |
Actions (login required)
 |
View Item |
