Using Machine Learning to Study the Structure of CryptoMarkets

Jonathan Bechtel

Details
In this meetup we'll study original research conducted inside the DSML group! The topic is finance, and it will go over how you can use different analytical techniques to study how assets are related in financial markets.
What are the most important assets in a broader financial ecosystem? Which ones serve as hubs, and others spokes? What portion of a market's behavior is "efficient", and how much of it can be arbitraged? How could you use algorithmic techniques to identify groups of assets to use for trading strategies?
This presentation will attempt to answer these questions and more!
The main topic of the paper will be the use of a graph technique called a minimum spanning tree, which can be built from different types of similarity to study how different financial assets to co-move together.
In this paper we'll apply this technique to a large swath of crypto assets with the aim of answering the following questions:
- What is the overall "shape" of the crypto market?
- What are the most important tokens in the crypto ecosystem?
- How stable and efficient is the crypto market compared to the traditional financial markets?
- How do different similarity measures affect the underlying graph representation of the crypto market?
- What are some practical techniques that can be implemented from the information discussed tonight?
This promises to be an engaging look at the financial ecosystem with a very algorithmic approach, and provide a unique way to study the world of cyryptomarkets in particular, and finance in general.
While this event is FREE, tickets are required & space is limited!
Attend this event