Arkadiusz Lipiecki, Rafał Weron
arXiv 31 Aug 2026 · Machine Learning
arXiv:2609.00089 · PDF · Extracted main text
Foundation models promise accurate forecasts with little or no task-specific training, but whether they can replace models designed specifically for electricity price forecasting remains unclear. We compare nine variants from five foundation model families, evaluated in zero-shot mode, with two state-of-the-art electricity price forecasting benchmarks in Germany, Poland, and Spain over 2021-2025. Their performance is assessed in terms of point and probabilistic forecasting accuracy, as well as economic value in battery energy storage arbitrage. Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets and all statistical measures. However, this statistical dominance does not translate directly into economic dominance: TabPFN performs best under unlimited bids and riskier quantile-based strategies, whereas the Distributional Deep Neural Network benchmark is more profitable when risk tolerance is lower. Thus, foundation models cannot universally replace market-specific models, and their value depends on both model architecture and the decision problem.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | G. Marcjasz and M. Narajewski and R. Weron and F. Ziel (2023) Distributional neural networks for electricity price forecasting self | 1.000 | 12 | 6 | 100% |
| 2 | Jesus Lago and Grzegorz Marcjasz and Bart De Schutter and Rafał Weron (2021) Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark self | 1.000 | 8 | 4 | 100% |
| 3 | Marchesi, G. and Ballarino, A. and Brusaferri, A (2025) Assessing Time Series Foundation Models for Probabilistic Electricity Price Forecasting: Toward a Unified Benchmark | 0.928 | 4 | 3 | 100% |
| 4 | Katarzyna Maciejowska and Bartosz Uniejewski and Rafal Weron (2023) Forecasting Electricity Prices self | 0.843 | 3 | 3 | 100% |
| 5 | Simon Hirsch and Florian Ziel (2026) Probabilistic forecasting for day-ahead electricity prices, battery trading strategies and the economic evaluation of predictive… | 0.811 | 4 | 2 | 100% |
| 6 | Ponyuenyong, K. and Tu, P. and Tan, J. W. and Cheong, W. S. and Ng S… (2026) Day-Ahead Electricity Price Forecasting for Volatile Markets Using Foundation Models with Regularization Strategy | 0.811 | 4 | 2 | 100% |
| 7 | Das, Abhimanyu and Kong, Weihao and Sen, Rajat and Zhou, Yichen (2024) A decoder-only foundation model for time-series forecasting | 0.737 | 3 | 2 | 100% |
| 8 | Hornek, Timothée and Sartipi, Amir and Tchappi, Igor and Fridgen, Gi… (2025) Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting | 0.737 | 3 | 2 | 100% |
| 9 | Lipiecki, Arkadiusz and Uniejewski, Bartosz and Weron, Rafał (2024) Postprocessing of point predictions for probabilistic forecasting of day-ahead electricity prices: The benefits of using isotoni… self | 0.737 | 3 | 2 | 100% |
| 10 | B. Uniejewski and R. Weron Regularized Quantile Regression Averaging for probabilistic electricity price forecasting self | 0.737 | 3 | 2 | 100% |
Showing the top 10 of 62 scored citations.