Please use this identifier to cite or link to this item: http://repository.ipb.ac.id/handle/123456789/155413
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorJulianto, Mochamad Tito-
dc.contributor.authorMatra, Emyr Aurelio-
dc.date.accessioned2024-08-02T01:25:38Z-
dc.date.available2024-08-02T01:25:38Z-
dc.date.issued2024-
dc.identifier.urihttp://repository.ipb.ac.id/handle/123456789/155413-
dc.description.abstractKemampuan 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).-
dc.description.abstractThe 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).-
dc.description.sponsorshipnull-
dc.language.isoid-
dc.publisherIPB Universityid
dc.titleImplementasi Metode Random Forest dan XGBoost untuk Memprediksi Arah Harga Penutupan Cryptocurrency Bitcoinid
dc.title.alternativeImplementation of the Random Forest and XGBoost Methods to predict the direction of closing prices on bitcoin cryptocurrencies-
dc.typeSkripsi-
dc.subject.keywordmachine learningid
dc.subject.keywordrandom forestid
dc.subject.keywordXGBoostid
dc.subject.keywordcryptocurrencyid
dc.subject.keywordbitcoinid
Appears in Collections:UT - Mathematics

Files in This Item:
File Description SizeFormat 
cover_G54170060_ffff5052b4c14d98b577e6610db6874c.pdfCover480.15 kBAdobe PDFView/Open
fulltext_G54170060_61f75eb381ae45c59f10dc54c8085ce6.pdf
  Restricted Access
Fulltext2.02 MBAdobe PDFView/Open
lampiran_G54170060_bca9f5b5bbde45fc91bb751b17f37fb2.pdf
  Restricted Access
Lampiran285.1 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.