XAI Reveals Key Drivers in European Electricity Market Prices

Antoine Pesenti, Aidan O'Sullivan· June 18, 2026 View original

Summary

This paper combines deep neural networks with explainable AI (XAI) techniques like SHAP to analyze electricity price determinants across 39 European bidding zones. The analysis identifies renewable energy sources, gas prices, and interconnections as crucial factors shaping price dynamics.

Researchers have developed a new methodology to understand the complex factors influencing electricity prices across Europe. By integrating deep neural networks with explainable AI tools, specifically SHAP, they can now interpret the predictions made by these powerful models. This approach allows for a clearer identification of the underlying drivers of price formation in a highly interconnected market. The study found that renewable energy sources, particularly solar, have a significant impact on price formation despite their current share in total generation. Gas prices remain a consistently dominant factor, and the strong interdependencies between European electricity systems, facilitated by interconnections, play a crucial role in shaping price dynamics. The research also explored a hypothetical fully integrated EU-wide market.

Why it matters

Professionals in energy trading, policy-making, and infrastructure planning can leverage these insights to better predict market behavior, optimize energy strategies, and design more resilient and efficient electricity grids. Understanding these drivers is crucial for navigating volatile energy markets and transitioning to sustainable energy sources.

How to implement this in your domain

  1. 1Integrate XAI tools like SHAP into existing energy market forecasting models to gain interpretability.
  2. 2Utilize identified key drivers (renewables, gas prices, interconnections) for more informed trading and investment decisions.
  3. 3Develop policy recommendations based on the impact of renewable energy and market interdependencies.
  4. 4Simulate counterfactual scenarios, such as a fully integrated market, to assess potential future market structures.

Who benefits

EnergyUtilitiesFinanceGovernment

Key takeaways

  • XAI techniques can provide critical interpretability for complex electricity market models.
  • Renewable energy sources, especially solar, disproportionately influence electricity prices.
  • Gas prices and cross-border interconnections are consistent and dominant drivers of European electricity prices.
  • Understanding these drivers is essential for market forecasting, policy development, and grid optimization.

Original post by Antoine Pesenti, Aidan O'Sullivan

"arXiv:2606.19118v1 Announce Type: new Abstract: Electricity markets are inherently complex systems characterised by strong nonlinearities, high-dimensional interactions, and increasing interdependence across regions. While deep neural networks (DNNs) have demonstrated strong pred…"

View on X

Originally posted by Antoine Pesenti, Aidan O'Sullivan on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses