Our approach is data-driven and powered by advanced AI technology. We integrate insights from over 10 weather models and internally combine multiple power
forecasting models for greater accuracy.
These solutions are specifically tailored for short-term power trading, optimized at both portfolio and asset levels. They efficiently handle operational data, such as SCADA metrics and availability information, ensuring optimal decision-making.
Our automated bidding strategies leverage price forecasts to strategically trade energy volumes on a day-ahead or intraday basis, maximizing short-term trading profits.
This data-driven, AI-powered approach utilizes advanced price forecasting models, which incorporate dozens of external data sources, including weather models and fundamental market data. These external inputs are integrated with internal models that utilize over a hundred internally developed features, resulting in highly optimized trading decisions.
VAR less than 6% Our model operates with a daily objective to maintain peak efficiency and risk control.
365 days Trading days (vs 220 in capital markets) result in higher Sharpe ratio.
Aleksandr , an MIT graduate with degrees in Mathematics and Electrical Engineering/Computer Science, boasts over 7 years of experience as a treasuries trader at Deutsche Bank. There, he developed and managed proprietary trading models for the US Treasuries market and created a successful automatic market-making system.
Slava Kuznetsov, with a master’s degree in Applied Mathematics and Artificial Intelligence, has over a decade of experience as a model strategist on the front desks of top financial institutions, including BNP, Deutsche Bank, and Merrill Lynch. He is a recognized authority in the creation of industrial high-frequency trading systems.