Walnut AI trains massive amounts of natural language text data based on deep learning, extracts models and patterns from it, and continues to 

provide reference samples for trade to achieve higher annualized returns. In order to further improve the Walnut project, we will effectively 

launch AI quantitative trading and promote the opening of a new era of quantification.

1. Cloud research

Walnut's cloud-based research terminal attaches terabytes of financial, fundamental and alternative data that is pre-formatted and ready for use. 

Alternative data is linked to the underlying securities and is labeled FIGI, CUSIP and ISIN to facilitate building strategies. Access popular machine 

learning and feature selection libraries to quantify factor importance. Install custom packages as required.

2. Backtesting

Move from research to point-in-time, fee, slippage and spread-adjusted backtesting on lightning-fast cloud core with minimal to no code changes. 

Multi-asset backtesting of portfolios consisting of thousands of securities using realistic margin models. Import custom and alternative data linked 

to underlying securities to realistically simulate live trading portfolios and avoid common pitfalls like forward-looking bias. Our technology is 

field-proven through thousands of unit and regression tests, with over 15,000 backtests performed daily on QuantConnect.

3. Parameter optimization

Our parameter sensitivity testing allows you to run thousands of complete backtests on our scalable cloud computing, completing weeks of work in 

minutes. Visualize all iterations of parameters on a heat map to quickly understand your strategy's sensitivity to parameters for robust out-of-sample 

trading. Explore further by opening each result and viewing its individual trading and backtest logs to fully understand the source of your alpha.

4. Institutional-level real-time trading

Since 2021, Walnut has deployed over 250,000 live strategies into hosted, co-located live trading environments. Our platform handles over $1 billion 

in notional trading volume each month. Execute trades directly through our 15 integrations or EMSX Net’s 1,300 liquidity providers. Our live feed 

includes US Coinbase, Biance, OKX and major cryptocurrency exchanges. Other live feed options are available upon request.

The Walnut protocol ecological AI quantitative trading focuses on artificial intelligence, including: Al collecting and processing market data, AI trading 

models, Al executing trading strategies, and AI risk management, which can improve the accuracy and efficiency of its trading models and help it 

formulate effective trading strategies, achieve higher trading efficiency and faster response speed, help reduce trading risks and increase returns.

All in all, Walnut's launch of AI quantitative trading is of great significance. It not only provides convenience for market transactions, but also promotes 

the opening of a new era of quantification.