BUDIYANA, IRVAN PUTRA (2025) KOMPARASI PREDIKSI HARGA BITCOIN MENGGUNAKAN ALGORITMA KNN DAN SVM. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (364kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (45kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (232kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (170kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (551kB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (30kB) |
|
|
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (95kB) |
|
|
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (863kB) |
Abstract
Limited public knowledge about Bitcoin Halving often triggers Fear of Missing Out (FOMO), leading individuals to invest without understanding the risks and market volatility. Bitcoin Halving is a periodic event that halves mining rewards, impacting Bitcoin's price and scarcity. This study aims to analyze Bitcoin price trends before and after Halving and evaluate the Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) algorithms in predicting its impact. Using a predictive approach, the study employs historical Bitcoin price data, including variables such as date, opening price, high price, low price, volume, percentage change, and U.S. interest rates. SVM and KNN are chosen for their ability to process complex and non-linear data. Model performance is assessed using Mean Square Error (MSE) and Root Mean Square Error (RMSE) to measure prediction accuracy. The research also explores the relationship between macroeconomic variables, such as interest rates, and Bitcoin price fluctuations. The findings aim to provide insights into the strengths and weaknesses of each algorithm while helping individuals manage investment risks more effectively. Key Search: Bitcoin Halving, Market Volatility, SVM, KNN, Price Prediction, Cryptocurrency, Investment Risk, Interest Rates Minimnya pengetahuan masyarakat tentang momen Halving Bitcoin sering menyebabkan terjadinya Fear of Missing Out (FOMO), di mana banyak orang berinvestasi tanpa memahami risiko dan volatilitas pasar. Halving Bitcoin merupakan peristiwa yang mengurangi hadiah blok bagi penambang hingga setengahnya, yang dapat memengaruhi harga dan kelangkaan Bitcoin. Penelitian ini bertujuan untuk menganalisis pola perubahan harga Bitcoin sebelum dan sesudah Halving serta mengevaluasi algoritma Support Vector Machine (SVM) dan KNearest Neighbor (KNN) dalam memprediksi dampak peristiwa tersebut. Melalui pendekatan prediktif, penelitian menggunakan data historis Bitcoin, mencakup variabel seperti tanggal, harga terakhir, harga pembukaan, harga tertinggi, harga terendah, volume, perubahan persentase, dan suku bunga Amerika Serikat. Algoritma SVM dan KNN dipilih karena kemampuannya menangani data kompleks dan non-linear. Kinerja model dievaluasi menggunakan Mean Square Error (MSE) dan Root Mean Square Error (RMSE) untuk mengukur akurasi prediksi. Penelitian juga mengkaji hubungan antara variabel makroekonomi, seperti suku bunga, dengan fluktuasi harga Bitcoin. Hasil diharapkan memberikan wawasan tentang keunggulan dan kelemahan masing-masing algoritma serta membantu masyarakat mengelola risiko investasi secara lebih bijak. Kata kunci: Halving Bitcoin, Volatilitas Pasar, SVM, KNN, Prediksi Harga, Cryptocurrency, Risiko Investasi, Suku Bunga
Actions (login required)
 |
View Item |
