Nathania, Vannesa (2026) Prediksi Harga dan Risiko Kerugian Cryptocurrency Ethereum Melalui Metode Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS). Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (cover)
22083010044-cover.pdf Download (1MB) | Preview |
|
|
Text (bab 1)
22083010044-bab1.pdf Download (261kB) | Preview |
|
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (bab 2)
22083010044-bab2.pdf Restricted to Repository staff only until 15 May 2028. Download (976kB) | Request a copy |
|
|
Text (bab 3)
22083010044-bab3.pdf Restricted to Repository staff only until 15 May 2028. Download (951kB) | Request a copy |
|
|
Text (bab 4)
22083010044-bab4.pdf Restricted to Repository staff only until 15 May 2028. Download (5MB) | Request a copy |
|
|
Text (bab 5)
22083010044-bab5.pdf Download (244kB) | Preview |
|
|
Text (daftar pustaka)
22083010044-daftar pustaka.pdf Download (199kB) | Preview |
|
|
Text (lampiran)
22083010044-lampiran.pdf Restricted to Repository staff only until 15 May 2028. Download (174kB) | Request a copy |
Abstract
Crypto assets are one of the most popular investment instruments in the current digital era, with growth reaching 335.9% by 2024. Crypto assets have highly volatile price characteristics, so conventional predictive modeling is often unable to capture complex price movement patterns. This condition creates the need for price prediction methods that are adaptive and sensitive to price dynamics. This study aims to implement an Ethereum price prediction method using a deep learning approach through the Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS) model, a time series model capable of providing good prediction results. The analysis was conducted univariately using historical Ethereum (ETH) closing price data for the period November 9, 2017, to January 31, 2025, obtained from the yfinance platform. Model performance evaluation was carried out using MAPE, RMSE, MAE, and directional accuracy. The urgency of this research lies in the application of the N-HiTS model to data with high volatility levels such as Ethereum. The research gap in this study is the application of investment risk analysis using Value at Risk with historical simulation methods. This research aims to provide Ethereum price predictions and investment risks that can be used as a reference for investors and other stakeholders in making more informed decisions. The results showed a MAPE value of 3.13%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76.6 Computer Programming | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Vannesa Nathania | ||||||||||||
| Date Deposited: | 19 May 2026 07:09 | ||||||||||||
| Last Modified: | 19 May 2026 07:31 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/51607 |
Actions (login required)
 |
View Item |