APPLICATION OF SINGULAR SPECTRUM ANALYSIS (SSA) FOR FORECASTING ETHEREUM CRYPTOCURRENCY PRICES

VEGA IVANKA VIVANA, . (2025) APPLICATION OF SINGULAR SPECTRUM ANALYSIS (SSA) FOR FORECASTING ETHEREUM CRYPTOCURRENCY PRICES. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

[img] Text
File COVER.pdf

Download (1MB)
[img] Text
File BAB 1.pdf

Download (179kB)
[img] Text
File BAB 2.pdf
Restricted to Registered users only

Download (686kB) | Request a copy
[img] Text
File BAB 3.pdf
Restricted to Registered users only

Download (265kB) | Request a copy
[img] Text
File BAB 4.pdf
Restricted to Registered users only

Download (902kB) | Request a copy
[img] Text
File BAB 5.pdf
Restricted to Registered users only

Download (183kB) | Request a copy
[img] Text
File DafPus.pdf

Download (200kB)
[img] Text
File Lampiran.pdf
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

The rapid growth and volatility of cryptocurrency markets, especially Ethereum, present both opportunities and challenges for investors and traders. This study explores the application of Singular Spectrum Analysis (SSA) for forecasting Ethereum's daily closing prices in USD. SSA is a powerful, non-parametric time series analysis method capable of decomposing data into trend, seasonal, and noise components without requiring strong statistical assumptions. Using Ethereum price data from February 3 to April 23, 2025, the study divides the dataset into in-sample (75\%) and out-of-sample (25\%) segments. The decomposition and reconstruction processes successfully identify distinct trend and seasonal structures. Forecasting was performed for the next 20 days using the Linear Recurrent Formula (LRF), and model accuracy was evaluated using the Mean Absolute Percentage Error (MAPE). The results demonstrate SSA’s effectiveness in short-term cryptocurrency forecasting, with a low MAPE indicating high predictive accuracy. The findings suggest that SSA is a viable alternative to traditional models in volatile financial environments and can support better-informed decision-making for crypto investors. Keywords: Singular Spectrum Analysis (SSA), Ethereum, time series forecasting, cryptocurrency, price prediction. ABSTRAK Pertumbuhan pesat dan volatilitas pasar cryptocurrency, khususnya Ethereum, memberikan peluang dan tantangan bagi para investor dan trader. Penelitian ini mengeksplorasi penerapan Singular Spectrum Analysis (SSA) untuk meramalkan harga penutupan harian Ethereum dalam USD. SSA adalah metode analisis deret waktu non-parametrik yang kuat yang mampu mendekomposisi data menjadi komponen tren, musiman, dan noise tanpa memerlukan asumsi statistik yang kuat. Menggunakan data harga Ethereum dari 3 Februari hingga 23 April 2025, penelitian ini membagi dataset menjadi segmen dalam-sampel (75\%) dan luar-sampel (25\%). Proses dekomposisi dan rekonstruksi berhasil mengidentifikasi struktur tren dan musiman yang jelas. Peramalan dilakukan untuk 20 hari berikutnya menggunakan Linear Recurrent Formula (LRF), dan akurasi model dievaluasi menggunakan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan efektivitas SSA dalam peramalan cryptocurrency jangka pendek, dengan MAPE yang rendah menunjukkan akurasi prediksi yang tinggi. Temuan ini menunjukkan bahwa SSA merupakan alternatif yang layak dibandingkan model tradisional dalam lingkungan keuangan yang volatil dan dapat mendukung pengambilan keputusan yang lebih baik untuk investor crypto. Kata kunci: Singular Spectrum Analysis (SSA), Ethereum, peramalan deret waktu, cryptocurrency, prediksi harga.

Item Type: Thesis (Sarjana)
Additional Information: 1). Dr. Yudi Mahatma, M.Si 2). Dr. Lukita Ambarwati, S.Pd, M.Si
Subjects: Sains > Matematika
Divisions: FMIPA > S1 Matematika
Depositing User: VEGA IVANKA VIVANA .
Date Deposited: 05 Aug 2025 06:38
Last Modified: 05 Aug 2025 06:38
URI: http://repository.unj.ac.id/id/eprint/57951

Actions (login required)

View Item View Item