Imamuddin, Muhammad Wahyu (2021) Analisis Atribut pada Sistem Prediksi Harga Emas Berbasis Multilayer Perception. Tugas Akhir thesis, University of Technology Yogyakarta.
|
Text
ABSTRAK_5160411049_MUHAMMAD WAHYU IMAMUDDIN.pdf Download (9kB) | Preview |
Abstract
BAB VI ABSTRACT Gold investment movement tends to be more stable and its value increases. In contrast to currency exchange investments. Gold is one type of commodity that is currently in great demand by investors because it is considered profitable. However, in practice an investor must be able to predict when the gold price will go down and when the gold price will rise so that he can determine when to buy and sell his gold. Therefore, the researcher developed a time series analysis system for gold price data to predict the future gold price based on the Multilayer Perceptron (MLP) using the Backpropagation Neural Network (BNN) algorithm. Gold data is used from 1979 - 2019. In the training process the training data is used from 1979 - 2015, while the test data is used from 2016 - 2019. After training and testing is carried out using the same architecture to predict the price of gold with 1 day , 7 days, 14 days, 21 days and 28 days ahead, it can be concluded that the farther the prediction period is, the higher the error rate will be. Keywords: Gold Price, Backpropagation, Multilayer Perceptron
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 26 Mar 2021 08:25 |
| Last Modified: | 26 Mar 2021 08:25 |
| URI: | http://eprints.uty.ac.id/id/eprint/7174 |
Actions (login required)
 |
View Item |
