Skripsi
DETEKSI TRANSAKSI ANOMALI PADA BLOCKCHAIN DENGAN MENGGUNAKAN METODE DEEP BELIEF NETWORK (DBN).
In recent years, blockchain technology has found widespread applications across various domains, including cryptocurrency, financial services, and risk management. Cryptocurrency, in particular, has garnered significant attention from investors, regulators, and the media ever since Bitcoin was first proposed by Nakamoto. This research utilizes a Deep Belief Network (DBN) to detect patterns of abnormal transactions (anomaly) in a dataset. The dataset was generated by extracting data spanning from 2011 to 2013 and balanced using oversampling and undersampling techniques. The best-performing model achieved an accuracy of 83.05%. Through k-fold validation, the model exhibited good consistency, with an average accuracy of 82.88%. These results indicate that the model maintains consistency and can be relied upon for the given detection task.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307006743 | T130853 | T1308532023 | Central Library (Referens) | Available |
No other version available