Seminar: Blockchain Data Analytics: Building Predictive Machine Learning Models with Topological Data Features
15 Nov 2018
11:00am - 12:30pm
Room 7-207, 7/F, Lau Ming Wai Academic Building

Over the last couple of years, Bitcoin cryptocurrency and the Blockchain technology that forms the basis of Bitcoin have witnessed an unprecedented attention. Designed to facilitate a secure distributed platform without central regulation, Blockchain is heralded as a novel paradigm that will be as powerful as Big Data, Cloud Computing, and Machine Learning. Blockchain continues to evolve, but its applications have already matured to rival, and already in some cases, replace more traditional institutions as avenues of global activity.

A unique Blockchain feature is that in contrast to fiat currencies, transactions of cryptocurrencies are permanently recorded on distributed ledgers to be seen by the public. As a result, public availability of all cryptocurrency transactions creates a complex network of public financial interactions that can be used to study not only the blockchain graph, but the relationship between various blockchain network features and their impact on risk investment, price dynamics, and assessment of market activity, in general. To understand the role of such local topological structures in blockchain graph, we introduce a novel concept of chainlets, or blockchain motifs. We show that chainlets as well as analysis of persistent homologies on chainlets, coupled with modern machine learning approaches, can advance our knowledge on cryptocurrency price formation and associated risk assessment, and offer an early warning mechanism for anomaly detection within crypto-ecosystem.