OpenGradient Research
OpenGradient, a trailblazer and leader in DeAI, is dedicated to advancing cutting-edge research in machine learning and artificial intelligence. With a strong commitment to innovation and quality, OpenGradient Research focuses on exploring a wide range of impactful applications of DeAI across various sectors. These applications include the development and analysis of models for decentralized finance DeFi, blockchain technologies, risk assessment, tokenomics, TradFi, anomaly detection, and more.
Our research aims to address real-world challenges by leveraging decentralized AI to create scalable, secure, and transparent solutions that benefit the broader AI and financial ecosystems. OpenGradient continuously pushes the boundaries of what DeAI can achieve by conducting thorough investigations and producing new insights and methodologies.
We invite you to check back regularly for the latest updates on our ongoing research, newly developed models, and insights into the evolving landscape of DeAI. Stay informed as we continue to share breakthroughs and advancements in this exciting and transformative field.
Current Research
Mitigating Risk and Loss in AMM Liquidity Pools: A Dynamic Fee System based on Risk Prediction
In decentralized finance, constant function market makers have transformed asset trading by enabling automated market making. However, the nature of static trading fees in CFMM models raises concerns about the long-term profitability of liquidity providers because LPs are not compensated for increased risk during volatile environments. We introduce a dynamic fee system that leverages a simple machine-learned model to forecast volatility and adjust fees in real time based on market conditions. Historical simulations show that a predictive dynamic fee model generates higher total collected fees for LPs compared to static fee structures. By adjusting fees according to market volatility, the model compensates LPs for increased risk during volatile periods, thereby enhancing their profitability and the attractiveness of liquidity provision in DeFi ecosystems.
In our simulation we find over 15% increase in total LP fees collected in both WETH and WBTC stablecoin pools. This significant increase demonstrates the value of AI/ML in the DeFi ecosystem. Final research forthcoming, see a draft here. You can also access the ETH model itself in OpenGradient Hub.
Anticipating Volatility and its Dynamics Over Varying Horizons
Information about future volatility can be useful in options pricing, risk management, portfolio optimization, and volatility sensitive trading. There is often a siloing of analysis of low, medium, and high frequency volatility. We analyze dynamics of volatility in crypto assets over multiple timeframes and demonstrate forward-looking volatility ANN models that that outperform simple current volatility and other common models over multiple risk horizons.
We find high performance of predictive volatility models. Research documentation and papers forthcoming! You can find the 1 hour model in in OpenGradient Hub.