Image of DETEKSI ANOMALI TRANSAKSI BITCOIN DENGAN METODE ISOLATION FOREST

Skripsi

DETEKSI ANOMALI TRANSAKSI BITCOIN DENGAN METODE ISOLATION FOREST

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Bitcoin, introduced in 2008 by Satoshi Nakamoto, is the first digital currency to use blockchain for secure transactions. Despite its popularity, challenges in detecting illegal or suspicious transactions arise due to lack of regulation and anonymity. This research employs the Isolation Forest algorithm to identify fraudulent Bitcoin transactions. Isolation Forest was chosen for its superiority in detecting anomalies in large and heterogeneous datasets, with the ability to handle high-dimensional and large-scale problems. The method was tested on a dataset of Bitcoin transactions from a specific period, which was then divided into training and testing data. Evaluation results show consistent levels of accuracy, precision, recall, and F1-score, albeit with a tendency to classify normal transactions as anomalies. Model evaluation indicates the best performance with a training data split of 30% and testing data split of 70%, yielding an accuracy of 96.56%, precision of 98.25%, recall of 98.35%, and F1-score of 98.24%. The findings of this study make a significant contribution to the development of fraud detection systems for digital currencies, particularly in addressing security and anomaly issues commonly associated with Bitcoin transactions.

Availability
Inventory Code Barcode Call Number Location Status
2407003741T146836T1468362024Central Library (REFERENCES)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1468362024
Publisher
Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer.,
Collation
xvii, 126 hlm.; ilus.; tab.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
005.207
Content Type
Text
Media Type
unmediated
Carrier Type
unspecified
Edition
-
Subject(s)
Prodi Sistem Komputer
deteksi anomali
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment