EconBase
← All papers

Probabilistic Forecasting for Day-ahead Electricity Prices, Battery Trading Strategies and the Economic Evaluation of Predictive Accuracy

Simon Hirsch, Florian Ziel

arXiv 21 Apr 2026 · Finance — Statistical Finance

arXiv:2604.19580 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Electricity price forecasting supports decision-making in energy markets and asset operation. Probabilistic forecasts are increasingly adopted to explicitly quantify uncertainty, typically issued as quantile predictions or ensembles of the full predictive distribution. However, how improvements in statistical forecast quality translate into economic value remains unclear. Battery storage arbitrage in day-ahead markets is a popular application-based benchmark for this purpose. We analyze quantile-based trading strategies (QBTS) and identify two critical flaws: they do not incentivize honest probabilistic forecasting and they ignore the intertemporal dependence structure of electricity prices. We therefore frame battery optimization as a stochastic program based on fully probabilistic forecasts and examine decision quality measurement for risk-neutral and risk-averse settings under different uncertainty models. Our discussion touches both sides of the coin: How reliable is the economic evaluation of forecasting models though (simplified) application studies - and how do improvements in statistical forecast quality for stochastic programs relate to the decision-quality and economic performance? We provide theoretical justification and empirical evidence from a case study on the German electricity market. Our results highlight the pitfalls of ranking forecasting models through battery trading strategies. We conclude with implications for evaluation practice and directions for future research in application-based forecast assessment.

Citation extraction

87
references
173
in-text mentions
87
distinct cited
12
self-citations
19,722
main-text words

appendix boundary found by appendix_command · 96% of the source is main text. Read the extracted text to check this.

Most heavily cited references

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.

ReferenceIntensityMentionsSectionsMain text
1Maciejowska, Katarzyna and Lipiecki, Arkadiusz and Uniejewski, Bartosz (2025) Statistical and economic evaluation of forecasts in electricity markets: beyond RMSE and MAE1.00096100%
2Gneiting, Tilmann and Raftery, Adrian E (2007) Strictly proper scoring rules, prediction, and estimation1.00084100%
3Uniejewski, Bartosz (2025) Smoothing quantile regression averaging: A new approach to probabilistic forecasting of electricity prices1.00084100%
4O’Connor, Ciaran and Collins, Joseph and Prestwich, Steven and Visen… (2025) Optimising quantile-based trading strategies in electricity arbitrage1.00073100%
5O’Connor, Ciaran and Bahloul, Mohamed and Rossi, Roberto and Prestwi… (2025) Conformal prediction for electricity price forecasting in the day-ahead and real-time balancing market1.00063100%
6Alexander, Carol and Coulon, Michael and Han, Yang and Meng, Xiaochun (2024) Evaluating the discrimination ability of proper multi-variate scoring rules0.92844100%
7Marcjasz, Grzegorz and Narajewski, Michał and Weron, Rafał and Ziel,… (2023) Distributional neural networks for electricity price forecasting self0.8434375%
8Buchweitz, Erez and Romano, João Vitor and Tibshirani, Ryan J (2025) Asymmetric penalties underlie proper loss functions in probabilistic forecasting0.84333100%
9Marcotte, Étienne and Zantedeschi, Valentina and Drouin, Alexandre a… (2023) Regions of reliability in the evaluation of multivariate probabilistic forecasts0.84333100%
10Nitka, Weronika and Weron, Rafał (2023) Combining predictive distributions of electricity prices: Does minimizing the CRPS lead to optimal decisions in day-ahead bidding?0.84333100%

Showing the top 10 of 87 scored citations.