Our Research

Quantifying Stablecoin Deviations and Infrastructure Integrity 

Analyzing the risk of holding stablecoins by investigating depegging problems, infrastructure integrity, and similarities to money market funds. 

Sentiment Analysis in Cryptocurrency Markets 

Leveraging the role of news for the cryptocurrency market sentiment in predicting volatility. Creating index-based features to leverage Natural Language Processing (NLP) models for forecasting.

Efficiency and Dynamics in Decentralized Exchanges 

Studying models for liquidity provision in Automated Market Making (AMM)-based Dexes, identifying differences with traditional order book-based exchanges, and analyzing pros and cons. Investigating price discovery mechanisms and improving automated liquidity management techniques.

Reinforcement Learning for Dynamic Position Management in Decentralized Finance 

Managing dynamic Uniswapv3 positions and moving windows to enhance liquidity management techniques through reinforcement learning. 

Prevention and Identification of Miner Etractable Value (MEV) Activities 

Studying the problem of MEV transactions and analyzing patterns. Creating algorithms to prevent and identify MEV activities, utilizing on-chain data. Aiming to understand and mitigate the risks associated with MEV in the blockchain ecosystem.

Cryptocurrency Volatility Forecasting

Utilizing a blend of classical econometric methods and cutting-edge techniques like graph neural networks to forecast the cryptocurrency market's volatility. Comparing these forecasts with more established asset classes, such as equities, to understand cryptocurrency volatility's unique dynamics and challenges.