https://orcid.org/0000-0001-9814-3883
![Sample our Information Science journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5940/TOC-Subject-Sample-2021-Communication-Studies.jpg"})
Abstract
Bitcoin is a cryptocurrency whose transactions are recorded on a distributed, openly accessible ledger. On the Bitcoin Blockchain, an owning entity’s real-world identity is hidden behind a pseudonym, a so-called address. Therefore, Bitcoin is widely assumed to provide a high degree of anonymity, which is a driver for its frequent use for illicit activities. This paper presents a novel approach for de-anonymizing the Bitcoin Blockchain by using Supervised Machine Learning to predict the type of yet-unidentified entities. We utilized a sample of 957 entities (with ≈385 million transactions), whose identity and type had been revealed, as training set data and built classifiers differentiating among 12 categories. Our main finding is that we can indeed predict the type of a yet-unidentified entity. Using the Gradient Boosting algorithm with default parameters, we achieve a mean cross-validation accuracy of 80.42% and F1-score of ≈79.64%. We show two examples, one where we predict on a set of 22 clusters that are suspected to be related to cybercriminal activities, and another where we classify 153,293 clusters to provide an estimation of the activity on the Bitcoin ecosystem. We discuss the potential applications of our method for organizational regulation and compliance, societal implications, outline study limitations, and propose future research directions. A prototype implementation of our method for organizational use is included in the appendix.
Supplemental Material
Supplemental data for this article can be accessed on the publisher’s website.
Notes
2. Tree algorithms: ID3, C4.5, C5.0 and CART.
3. Ensemble methods.
4. For example, German car manufacturer Daimler AG recently issued a e100 Million Corporate Bond on the blockchain [Citation66]. Also, Bitcoin has reached a trading volume corresponding to more than USD one bn/day [Citation57].
5. The ability to avoid the need for a trusted third party [Citation23].
6. See [Citation112] on the many different ways pseudonymous Blockchain technologies could revolutionize business and society.
8. Council and Parliament of the European Union: Amendment to directive (EU) 2015/849.
Additional information
Notes on contributors
Hao Hua Sun Yin
Hao Hua Sun Yin ([email protected]) is a Research Associate at the Center for Business Data Analytics of the Department of Digitalization at the Copenhagen Business School and a co-founder of Cryptium Labs GmbH, a digital and secure attestations as a service start-up for Proof-of-Stake blockchains such as Tezos, Cøsmos, and Polkadot. She worked previously as a data scientist and software engineer at Chainalysis, as a researcher at Cøsmos, and as a grant manager at the Ethereum Community Fund. Her research interests are in blockchain technology, applied cryptography for privacy and scalability of consensus algorithms, security in distributed and decentralized systems, and hardware, specifically hardware security modules. Her current research focuses on a generic mapping of the Blockchain ecosystem’s latest state, in terms of development and research. She holds a Master’s in Information Systems from the Copenhagen Business School (CBS).
Klaus Langenheldt
Klaus Langenheldt ([email protected]) is an Industrial Ph.D. Student at the Center for Business Data Analytics of the Department of Digitalization at CBS. He holds a M.Sc. in Business Administration and Information Systems (e-business) from that school, where he conducts research on de-anonymizing the Bitcoin Blockchain using supervised machine learning. In addition to his academic work, he brings extensive work experience from the IT sector, working—among others—as Business Developer for Europe’s largest incubator Rocket Internet and as Software Engineer for Danske Bank.
Mikkel Harlev
Mikkel Harlev ([email protected]) is a Research Associate at the Center for Business Data Analytics of the Department of Digitalization at CBS. He holds a M.S.c degree in Business Administration and Information Systems from CBS. He is currently employed as a software Engineer in the largest Danish bank, specializes in Data Science with a focus on its application in the financial sector, and conducts research on Bitcoin blockchain forensics and machine learning.
Raghava Rao Mukkamala
Raghava Rao Mukkamala ([email protected]) is an Associate Professor at the Center for Business Data Analytics of the Department of Digitalization at CBS and an associate professor at the Department of Technology, Kristiania University College, Denmark. He holds a Ph.D. degree from University of Copenhagen. Dr. Mukkamala’s research focuses on computational social science using an interdisciplinary approach, combining formal modelling approaches with data-mining/machine-learning techniques, for modelling of social science phenomena in digital transformation of organizations and society. He works with blockchain-based technologies for social business and Internet of Things. His research work is complemented by over ten years of professional experience in the Danish IT industry as a senior software engineer and consultant.
Ravi Vatrapu
Ravi Vatrapu ([email protected]; corresponding author) is a Professor of Computational Social Science at the Department of Digitalization, Copenhagen Business School; professor of applied computing at the Kristiania University College; and director of the Center for Business Data Analytics at CBS. He holds a Ph.D. in Communication and Information Sciences from the University of Hawaii at Manoa. Dr. Vatrapu’s research focus is on big social data analytics to design, develop, and evaluate a new holistic approach to computational social science, Social Set Analytics. He is the author of numerous publications in these domains.