View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Mathematics
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Mathematics
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Implementasi Metode Random Forest dan XGBoost untuk Memprediksi Arah Harga Penutupan Cryptocurrency Bitcoin

      Thumbnail
      View/Open
      Cover (480.1Kb)
      Fulltext (1.973Mb)
      Lampiran (285.1Kb)
      Date
      2024
      Author
      Matra, Emyr Aurelio
      Julianto, Mochamad Tito
      Metadata
      Show full item record
      Abstract
      Kemampuan dalam memprediksi tren pergerakan harga cryptocurrency bitcoin dengan baik dan akurat sangat penting bagi investor karena akan mempengaruhi keputusan untuk membeli atau menjual aset yang dapat menghasilkan keuntungan yang signifikan. Namun, karena harga cryptocurrency bitcoin cukup fluktuatif maka ada ketidakpastian yang harus diperhitungkan. Dalam beberapa tahun terakhir, algoritma machine learning khususnya algoritma pembelajaran gabungan telah digunakan untuk memprediksi arah harga penutupan cryptocurrency bitcoin. Hasil penelitian menunjukkan model random forest memberikan akurasi sebesar 90.75% dengan AUC sebesar 90% dan model XGBoost memberikan akurasi sebesar 90.12% dengan AUC sebesar 89%. Variabel fitur yang paling berpengaruh dari masing-masing model yaitu Moving Average Convergence Divergence (MACD) dan William Percentage Range (William%R).
       
      The ability to predict bitcoin cryptocurrency price movement trends well and accurately is very important for investors because it will influence decisions to buy or sell assets that can generate significant profits. However, because the price of the bitcoin cryptocurrency is quite volatile, there are exposures that must be taken into account. In recent years, machine learning algorithms especially federated learning algorithms have been used to predict the closing direction of the price of the cryptocurrency bitcoin. The research results show that the random forest model provides an accuracy of 90.75% with an AUC of 90% and the XGBoost model provides an accuracy of 90.12% with an AUC of 89% with the most influential feature variable from each model, namely Moving Average Convergence Divergence ( MACD) and William Percentage Range (William%R).
       
      URI
      http://repository.ipb.ac.id/handle/123456789/155413
      Collections
      • UT - Mathematics [1487]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository