Habibi, Mohammad Sufa Ammar (2026) REGRESI LOGISTIK DAN HISTORICAL SIMULATION VALUE AT RISK UNTUK ANALISIS MULTIDIMENSI SAHAM DAN KRIPTO. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
22083010014-Cover.pdf Download (815kB) | Preview |
|
|
Text (BAB 1)
22083010014-BAB 1.pdf Download (245kB) | Preview |
|
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB 2)
22083010014-BAB 2.pdf Restricted to Repository staff only until 7 July 2029. Download (638kB) |
|
|
Text (BAB 3)
22083010014-BAB 3.pdf Restricted to Repository staff only until 7 July 2029. Download (429kB) |
|
|
Text (BAB 4)
22083010014-BAB 4.pdf Restricted to Repository staff only until 7 July 2029. Download (1MB) |
|
|
Text (BAB 5)
22083010014-BAB 5.pdf Download (225kB) | Preview |
|
|
Text (Daftar pustaka)
22083010014-Daftar Pustaka.pdf Download (193kB) | Preview |
|
|
Text (Lampiran)
22083010014-Lampiran.pdf Restricted to Repository staff only until 7 July 2029. Download (278kB) |
Abstract
Investment in stocks and crypto assets in Indonesia has increased due to advances in technology and digital financial literacy. However, high volatility increases risk and uncertainty in decision-making. Previous studies generally analyze stocks and crypto assets separately, limiting a comprehensive understanding of their statistical characteristics, portfolio optimization, and extreme risk measurement. Therefore, an integrated investment analysis framework is needed. This study aims to identify the statistical characteristics of stocks and crypto assets, classify them, construct an optimal portfolio, and measure extreme investment risk. Daily price data from 30 IDX30 stocks and 30 crypto assets included in the CoinMarketCap 100 Index from July 23, 2023 to February 11, 2026 were analyzed using Factor Analysis, Logistic Regression, Mean Absolute Deviation (MAD), and Historical Simulation Value at Risk (HS-VaR). The novelty of this study lies in integrating these methods into a unified framework linking asset characterization, portfolio optimization, and extreme risk measurement. The results show that two factors explain 85.70% of total variation and achieve a classification accuracy of 93%, with the Tail Risk Factor serving as the primary differentiator between stocks and crypto assets. MAD optimization indicates that the Quadrant 2 Portfolio, characterized by a low Tail Risk Factor and a high Moment Factor, is the optimal portfolio with a Sharpe Ratio of 0.056404 and consists of ADRO.JK, AKRA.JK, TRX-USD, and LEO-USD. HS-VaR estimation at the 95% and 99% confidence levels indicates that the optimal portfolio remains exposed to potential extreme losses that should be considered in investment decision-making.
| 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: | Mohammad Sufa Ammar Habibi Habibi | ||||||||||||
| Date Deposited: | 07 Jul 2026 07:09 | ||||||||||||
| Last Modified: | 07 Jul 2026 07:09 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/54750 |
Actions (login required)
 |
View Item |