TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text
Abstract
Electricity price forecasting (EPF) supports scheduling, bidding, and risk management in electricity markets, yet existing benchmarks focus mainly on numerical inputs, leaving the forecasting value of forecast-time textual context insufficiently evaluated. We introduce TRACE, a reproducible benchmark of 7,300 zone--day instances pairing prices from five zones in a major U.S. market with official operational text available at the forecast cutoff. TRACE reconstructs official operational text at each cutoff, preventing post-cutoff information leakage. We evaluate TRACE for semantic alignment and forecasting value. Semantic assessments align with central movement and both tail risks in ground-truth prices, most consistently for upper-tail price risk. Forecasting value is reflected in a median 7.4\% reduction in upper-tail pinball loss across time-series foundation models. A controlled cross-day text-mismatch ablation reverses the gains, falling below the no-text baseline.
Related
- Online Conditional Vine Copulas: Forecasting Electricity Demand
- Combining Weather Forecast Aggregation and State-Space Models for Adaptive Probabilistic Electricity Load Forecasting
- Bi-Mamba-Load: A bidirectional structured state space model with sequence relationship adaptive perception for electricity load forecasting
- Day-Ahead Electricity Price Forecasting Using a Multivariate Group Lasso Method
- Long-term electricity load forecasting model based on multi-period and multi-scale analysis
BibTeX
@misc{yi2026trace,
title = {{TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text}},
author = {Xinyi Yi and Zhangdie Yuan and Ioannis Lestas},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.02256},
eprint = {2610.02256},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.02256},
}
RIS
TY - UNPB
TI - TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text
AU - Xinyi Yi
AU - Zhangdie Yuan
AU - Ioannis Lestas
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.02256
UR - https://arxiv.org/abs/2610.02256
AB - Electricity price forecasting (EPF) supports scheduling, bidding, and risk management in electricity markets, yet existing benchmarks focus mainly on numerical inputs, leaving the forecasting value of forecast-time textual context insufficiently evaluated. We introduce TRACE, a reproducible benchmark of 7,300 zone--day instances pairing prices from five zones in a major U.S. market with official operational text available at the forecast cutoff. TRACE reconstructs official operational text at each cutoff, preventing post-cutoff information leakage. We evaluate TRACE for semantic alignment and forecasting value. Semantic assessments align with central movement and both tail risks in ground-truth prices, most consistently for upper-tail price risk. Forecasting value is reflected in a median 7.4\% reduction in upper-tail pinball loss across time-series foundation models. A controlled cross-day text-mismatch ablation reverses the gains, falling below the no-text baseline.
ER -