NAINGGOLAN, GOVINDA (2023) PREDIKSI DATA TIME SERIES PADA VOLUME PEMBELIAN KELAPA SAWIT MENGGUNAKAN ALGORITMA LSTM. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (COVER)
01 COVER.pdf Download (539kB) | Preview |
|
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (122kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (166kB) |
|
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (170kB) |
|
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (129kB) |
|
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (119kB) |
|
|
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (218kB) |
|
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (1MB) |
Abstract
CPO production in Indonesia is increased due to the global market growing demands on vegetable oil. Because of this, the people in the palm oil processing industry are urged to keep production stable every week. To satisfy the need, PT Sawita Unggul Jaya, one of the palm oil processing companies in Indonesia, need the prediction of palm oil monthly production to organize their financial plan and production stability. The prediction is needed so that PT Sawita Unggul Jaya can estimate the next year production budget and prepare for the company production needs. LSTM Algorithm is used to achieve the prediction needed. LSTM algorithm proven to be beneficial for building data time series prediction model on palm oil monthly production. LSTM algorithm provide a good performance based on its MAPE accuracy rate that is 0.842582317339576. The number barely reach 10 that indicates the LSTM algorithm has high accuracy on the prediction results. Keywords : Prediction, Palm Oil, LSTM, Time Series Produksi CPO di Indonesia kian bertambah dikarenakan kebutuhan pasar global akan minyak nabati kian meningkat. Akibat meningkatnya kebutuhan akan itu, para pelaku industri dibidang pengolahan kelapa sawit didorong untuk menjaga produksi tetap stabil tiap minggunya. Untuk itu PT Sawita Unggul jaya harus melakukan prediksi produksi kelapa sawit perbulannya agar dapat mengatur rencana keuangan dan kestabilan produksi. Untuk dapat melakukan prediksi tersebut, maka dilakukan percobaan prediksi dengan menggunakan algortima LSTM. Penggunaan LSTM terbukti bermanfaat untuk membangun model peramalan data time series terhadap volume pembelian kelapa sawit. Algoritma LSTM memiliki performa yang baik karena menghasilkan tingkat akurasi MAPE sebesar 0.842582317339576. Angka tersebut menunjukkan bahwa algoritma LSTM ini memiliki tingkat prediksi yang akurat karena nilai masih dibawah batas 10. Hasil prediksi yang dihasilkan oleh model algoritma LSTM untuk 4 bulan mendatang yaitu kenaikan signifikan di bulan ke-2 lalu mengalami penurunan sebelum kembali naik, sedangkan untuk 8 bulan mendatang akan mengalami penurunan hingga bulan ke-5 sebelum naik secara bertahap. Kata Kunci : Prediksi, Kelapa Sawit, LSTM, Time Series
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO. 23 088 |
| NIM/NIDN Creators: | 41519010183 |
| Uncontrolled Keywords: | Prediksi, Kelapa Sawit, LSTM, Time Series |
| 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 > 003 Systems/Sistem-sistem 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: | CALVIN PRASETYO |
| Date Deposited: | 22 Sep 2023 01:48 |
| Last Modified: | 22 Sep 2023 01:48 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/81342 |
Actions (login required)
 |
View Item |
