Machine Learning and Blockchains

(This post will be updated with more information before the talk)

Tomorrow, April 11 2018, at 10:30 AM ET

Cognitive Systems Institute

Speaker: Awa Sun Yin

Talk: “Breaking Bad: De-Anonymising Entity Types on the Bitcoin Blockchain Using Supervised Machine Learning”

Slides.
Related article by author:  https://medium.com/@awasunyin/are-icos-a-bubble-blockchain-ecosystem-1eae4f02e404

Abstract: 

Bitcoin is a cryptocurrency whose transactions are recorded on a distributed, openly accessible ledger. On the Bitcoin Blockchain, an 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 reducing the anonymity of the Bitcoin Blockchain by using Supervised Machine Learning to predict the type of yet-unidentified entities. We utilised a sample of 434 entities (with z 200 million transactions), whose identity and type had been revealed, as training set data and built classifiers differentiating among 10 categories. Our main finding is that we can indeed predict the type of a yet-unidentified entity. Using  the Gradient Boosting algorithm, we achieve an accuracy of 77% and Fl-score of z 0.75 

Short bio: 

Awa Sun Yin is a data scientist during the day at Chainalysis, where she builds programs that leverage machine learning to extract intelligence from blockchain data. During the night, she coordinates and leads research at the Interchain Foundation in areas such as (but not limited to) cryptography, artificial intelligence, and formal verification. 

Chainalysis Inc    https://www.chainalysis.com/
" ... Our products are targeted at spotting connections between entities on the Bitcoin blockchain. We help Bitcoin businesses detect fraud and prevent money laundering, we help banks put in place adequate controls to bank Bitcoin businesses. ... " 

 ----------------------------

Cognitive Systems Institute Group Speaker Series Thursdays 10:30am US Eastern Time
Join the meetings by pointing your web browser to:  https://zoom.us/j/7371462221 ; Callin: (415) 762-9988 or (646) 568-7788 Meeting id 7371462221 ; International Numbers: https://zoom.us/zoomconference.

Join the CSIG LinkedIn Group to get reminders about talks and discuss them. Use twitter: #CSIGNews & #OpenTechAI
Replays before Dec 2015:  Dial 877.471.6587 or 402.970.2667 and enter the call’s Replay ID when prompted for a program ID number.   The Replay ID is listed in the Recording column of each date.