← Back to all news
arXiv Machine Learning By Xinyi Yi, Moy Yuan, Ioannis Lestas

TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text

Read the original on arXiv Machine Learning →

TRACE is a reproducible benchmark for electricity price forecasting that pairs 7,300 zone–day instances from five U.S. market zones with official operational text available at the forecast cutoff, ensuring no post‑cutoff information leakage. The benchmark evaluates semantic alignment and forecasting value, showing that the text aligns with central movement and tail risks in ground‑truth prices, especially for upper‑tail risk. Forecasting models using TRACE’s text achieve a median 7.4% reduction in upper‑tail pinball loss, while a controlled ablation that mismatches text reverses these gains.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 2

Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?

The study evaluates nine foundation model variants against two leading electricity price forecasting benchmarks across Germany, Poland, and Spain for 2021‑2025. Only the TabPFN models consistently outperform the benchmarks in both point and probabilistic accuracy, yet their economic advantage varies with bidding strategy and risk tolerance. The results indicate that foundation models cannot universally replace market‑specific models; their usefulness depends on the chosen architecture and the particular decision problem.

By Arkadiusz Lipiecki, Rafa{\l} Weron
benchmarks
More like this →
arXiv Machine Learning
Aug 19

Deep Learning for Cross-Border Electricity Price Forecasting: A Comparative Study

The paper presents a comparative study of six deep learning models—state-space, MLP, RNN, and Transformer-based architectures—for cross-border electricity price forecasting using publicly available data. It focuses on generalization across markets and evaluates performance under low-data target-market conditions (zero-shot, one-shot, few-shot) with a standardized dataset for the Germany‑Luxembourg bidding zone in 2024. Results show that N‑HiTS and NBEATSx perform competitively in limited‑data scenarios, while transformer models achieve comparable accuracy but require more adaptation and tuning, and that careful feature selection and hyperparameter tuning improve performance.

By Hadeer Elashhab, Sai Srijan Papineni, Marvin Dorn, Veit Hagenmeyer, Benjamin Sch\"afer
llmsbenchmarks
More like this →