Ashilla, Aurell Faza (2022) Peramalan Harga Emas Indonesia Menggunakan Metode ARIMA Dan Fuzzy Time Series Algoritma Model Chen. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211840000095-Undergraduate_Thesis.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Emas digunakan sebagai standar keuangan dan alat tukar yang diterima di seluruh negara. Emas dipilih sebagai instrument investasi karena risiko yang rendah, sifatnya yang likuid, dan harga yang tidak dipengaruhi oleh kebijakan suku bunga. Tujuan dari penelitian ini adalah untuk melakukan peramalan jangka pendek pada harga emas Indonesia dalam periode harian. Metode yang digunakan pada penelitian ini yaitu Autoregressive Integrated Moving Average (ARIMA) dan Fuzzy Time Series Algoritma Model Chen. Model ARIMA digunakan sebagai pembanding untuk mengetahui seberapa baik model komputasi fuzzy time series dapat meramalkan harga emas indonesia dibandingkan dengan model klasik statistika. Berdasarkan analisis yang dilakukan, pada model dugaan ARIMA asumsi normalitas tidak terpenuhi. Hal ini mengindikasikan terdapat outlier pada data historis sehingga outlier dimasukkan ke dalam model dan menghasilkan model ARIMA(0,0,5) outlier. Model terbaik untuk peramalan harga emas Indonesia periode harian adalah dengan Fuzzy Time Series Model Chen karena memiliki nilai RMSE, MAPE, dan MAD yang lebih kecil dibandingkan dengan model ARIMA. Berdasarkan hasil penelitian, harga emas Indonesia pada hari kerja di minggu pertama bulan Desember 2021 akan mengalami kenaikan harga emas sebelumnya.
================================================================================================
Gold is used as the financial standard and accepted medium of exchange throughout the country. Gold was chosen as an investment instrument because of its low risk, liquid nature, and price that is not influenced by interest rate policies. The purpose of this study is to perform short-term forecasts on the price of Indonesian gold in a daily period. The method used in this research is Autoregressive Integrated Moving Average (ARIMA) and Fuzzy Time Series Algorithm Chen's Model. The ARIMA model is used as a comparison to find out how well the fuzzy time series computational model can predict Indonesian gold prices compared to the classical statistical model. Based on the analysis conducted, the ARIMA conjecture model assumes normality is not met. This indicates that there are outliers in historical data so that outliers are included in the model and produce an ARIMA(0,0,5) outlier model. The best model for forecasting Indonesian gold prices daily is the Chen Fuzzy Time Series Model because it has smaller RMSE, MAPE, and MAD values compared to the ARIMA model. Based on the results of the study, the price of Indonesian gold in the first week of December 2021 will experience an increase in the previous gold price.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | ARIMA, Fuzzy Time Series, Harga Emas, Investasi, Peramalan, Forecasting, Gold Price, Invest |
| Subjects: | Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA280 Box-Jenkins forecasting Q Science > QA Mathematics > QA9.64 Fuzzy logic Q Science > QA Mathematics > QA248_Fuzzy Sets |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Aurell Faza Ashilla |
| Date Deposited: | 22 Feb 2022 01:25 |
| Last Modified: | 18 Jun 2024 13:26 |
| URI: | http://repository.its.ac.id/id/eprint/94682 |
Actions (login required)
 |
View Item |