Muhammad Faris Ramadhan, . (2024) PERBANDINGAN PERFORMA PERAMALAN HARGA BERAS PADA HISTORICAL DATA NASDAQ MENGGUNAKAN RANDOM FOREST DAN RECURRENT NEURAL NETWORK. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (19kB) |
|
Text
AWAL.pdf Download (702kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (192kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (407kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (145kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (78kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (158kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (90kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (9MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (667kB) |
Abstract
The price of rice which continues to rise along with the prolonged dry season in 2023 is a significant problem for the Indonesian people. The erratic increase in rice commodity prices has caused unrest among the public. As a student majoring in Computer Science, the researcher wants to predict future increases in rice commodity prices using Machine Learning and Deep Learning techniques. This research aims to compare the performance of rice price forecasting using the Random Forest and Recurrent Neural Network (RNN) methods based on historical Nasdaq data from January 2020 to December 2023. The data used is 1458 data divided into a training data ratio of 80% and test data 20% . The research results show that the RNN model provides the best prediction results with an RMSE of 0.2281, MAPE of 0.9941, and an R² value of 91% for all historical data. The Random Forest model provides close results with an RMSE of 0.2462, MAPE of 0.9949, and an R² value of 90%. In post-pandemic data (2022-2023), the RNN model again shows the best performance with an RMSE of 0.1457, a MAPE of 0.6577, and an R² value of 95%, while the Random Forest model produces an RMSE of 0.1488, a MAPE of 0 .6885, and an R² value of 94%. This research produces an RNN method that is superior to Random Forest for predicting or forecasting rice commodity prices based on historical Nasdaq data, which can be one of the considerations in designing rice export and import prices in Indonesia.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010511138] [Pembimbing 1: Ridwan Raafi'udin] [Pembimbing 2: Theresia Wati] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Novi Trisman Hadi] |
| Uncontrolled Keywords: | Rice price forecasting, Random Forest, Recurrent Neural Network, Historical Data Nasdaq, MAPE, RMSE, R2 |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | MUHAMMAD FARIS RAMADHAN |
| Date Deposited: | 05 Sep 2024 02:48 |
| Last Modified: | 05 Sep 2024 02:48 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31561 |
Actions (login required)
 |
View Item |