Anomaly detection has been a well-studied area for a long time. Its applications in the financial sector have aided in identifying suspicious activities of hackers. How- ever, with the advancements in the financial domain such as blockchain and artificial intelligence, it is more challenging to deceive financial systems. Despite these technological advancements many fraudulent cases have still emerged.
Many artificial intelligence techniques have been proposed to deal with the anomaly detection problem; some results appear to be considerably assuring, but there is no explicit superior solution. This repo is for a research that leaps to bridge the gap between artificial intelligence and blockchain by pursuing various anomaly detection techniques on transactional network data of a public financial blockchain ’Bitcoin’.
This repository is an implementation for a research that presents anomaly detection in the light of blockchain technology and its applications in the financial sector. It extracts the transactional data of bitcoin blockchain and analyses for malicious transactions using unsupervised machine learning techniques. A range of algorithms such as iso- lation forest, histogram based outlier detection (HBOS), cluster based local outlier factor (CBLOF), principal component analysis (PCA), K-means, deep autoencoder networks and ensemble method are evaluated and compared.
URL: http://urn.fi/URN:NBN:fi:tuni-201912056592
Bitcoin transaction network metadata dataset: https://ieee-dataport.org/open-access/bitcoin-transaction-network-metadata-2011-2013
Bitcoin transactions dataset: https://ieee-dataport.org/open-access/bitcoin-transactions-data-2011-2013
Bitcoin hacks/frauds dataset: https://ieee-dataport.org/open-access/bitcoin-hacked-transactions-2010-2013
-
Bitcoin Hacked Transactions 2010-2013:* https://www.kaggle.com/omershafiq/bitcoin-hacks-2010to2013
-
Bitcoin Network Transactional Metadata 2011-2013:* https://www.kaggle.com/omershafiq/bitcoin-network-transactional-metadata
This data is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
