IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2604.12082.html

When Forecast Accuracy Fails: Rank Correlation and Decision Quality in Multi-Market Battery Storage Optimization

Author

Listed:
  • Alessandro Falezza

Abstract

Battery energy storage systems (BESS) participating in multi-market electricity trading require price forecasts to optimize dispatch decisions. A widely held assumption is that forecast accuracy, measured by standard metrics such as mean absolute error (MAE), drives trading performance. We challenge this assumption using a hierarchical three-layer optimization system trading simultaneously on frequency containment reserve (FCR), automatic frequency restoration reserve (aFRR), day-ahead, and continuous intraday (XBID) markets in Germany and Switzerland over 2020-2025, with real market data from Regelleistung.net and Swissgrid. We find that rank correlation (Kendall tau), rather than MAE, is the primary predictor of intraday dispatch value: forecasts above an empirical threshold of tau approximately 0.85-0.95 capture up to 97-100% of perfect-foresight revenue, while persistence forecasts with near-zero tau capture only 33%. This threshold is stable across market regimes and volatility levels, and reflects the ordinal structure of the dispatch problem. Furthermore, under reserve market constraints, FCR capacity revenue exceeds XBID by 6.5x per MW, making capacity allocation -- not forecast accuracy -- the primary driver of total revenue. In the Swiss market, hydrological surplus anomalies are significantly associated with balancing market revenue (p = 0.0005), a mechanism absent from existing German-focused literature. These findings reframe forecast evaluation for BESS operators: the relevant question is not what the MAE is, but whether the forecast achieves tau-sufficiency.

Suggested Citation

  • Alessandro Falezza, 2026. "When Forecast Accuracy Fails: Rank Correlation and Decision Quality in Multi-Market Battery Storage Optimization," Papers 2604.12082, arXiv.org, revised Apr 2026.
    • Handle: RePEc:arx:papers:2604.12082
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2604.12082
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Massaro, Alessandro & Giardinelli, Vito O. M. & Cosoli, Gabriele & Magaletti, Nicola & Leogrande, Angelo, 2022. "The Prediction of Hypertension Risk," MPRA Paper 113242, University Library of Munich, Germany.
    2. David Schaurecker & David Wozabal & Nils Lohndorf & Thorsten Staake, 2025. "Maximizing Battery Storage Profits via High-Frequency Intraday Trading," Papers 2504.06932, arXiv.org, revised Aug 2025.
    3. Anish Nair & Ramkumar P. & Sivasubramanian Mahadevan & Chander Prakash & Saurav Dixit & Gunasekaran Murali & Nikolai Ivanovich Vatin & Kirill Epifantsev & Kaushal Kumar, 2022. "Machine Learning for Prediction of Heat Pipe Effectiveness," Energies, MDPI, vol. 15(9), pages 1-14, April.
    4. Yunxiao Deng & Suvrajeet Sen, 2022. "Predictive stochastic programming," Computational Management Science, Springer, vol. 19(1), pages 65-98, January.
    5. Harris, Richard D.F. & Shen, Jian & Yilmaz, Fatih, 2022. "Maximally predictable currency portfolios," Journal of International Money and Finance, Elsevier, vol. 128(C).
    6. Chu, Pyung Kun & Hoff, Kristian & Molnár, Peter & Olsvik, Magnus, 2022. "Crude oil: Does the futures price predict the spot price?," Research in International Business and Finance, Elsevier, vol. 60(C).
    7. Dang, Man & Henry, Darren & Thai, Hong An & Vo, Xuan Vinh & Mazur, Mieszko, 2022. "Does policy uncertainty predict the death of M&A deals?," Finance Research Letters, Elsevier, vol. 46(PB).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Niklas Dahlen, 2025. "Earnouts in mergers and acquisitions: a systematic literature review of a contingent payment mechanism," Management Review Quarterly, Springer, vol. 75(3), pages 2107-2146, September.
    2. Jiajun Xu & Suvrajeet Sen, 2024. "Ensemble Variance Reduction Methods for Stochastic Mixed-Integer Programming and their Application to the Stochastic Facility Location Problem," INFORMS Journal on Computing, INFORMS, vol. 36(2), pages 587-599, March.
    3. Bouteska, Ahmed & Hajek, Petr & Fisher, Ben & Abedin, Mohammad Zoynul, 2023. "Nonlinearity in forecasting energy commodity prices: Evidence from a focused time-delayed neural network," Research in International Business and Finance, Elsevier, vol. 64(C).
    4. Foteini Kyriazi & Sophia Tarani & Dimitrios D. Thomakos, 2025. "Median-adaptive portfolios: a minimum criteria approach to asset allocation," Annals of Operations Research, Springer, vol. 353(1), pages 377-400, October.
    5. Cañon, Carlos & Gerba, Eddie & Pambira, Alberto & Stoja, Evarist, 2024. "An unconventional FX tail risk story," Journal of International Money and Finance, Elsevier, vol. 148(C).
    6. Hye Rin Um & Fathey Mohammed & Narishah Mohamed Salleh & Mikkay Ei Leen Wong & Ibrahim T. Nather Khasro, 2026. "Optimal Methodology Settings for Developing Revenue Prediction Models," SN Operations Research Forum, Springer, vol. 7(1), pages 1-37, March.
    7. Perafán-Peña, Héctor Fabio & Gill-de-Albornoz Noguer, Belén & Giner, Begoña, 2024. "Targets’ earnings management and ownership decisions in M&A: Can less be more ?," Finance Research Letters, Elsevier, vol. 62(PA).
    8. Huafang Huang & Sharafat Ali & Yasir Ahmed Solangi, 2023. "Analysis of the Impact of Economic Policy Uncertainty on Environmental Sustainability in Developed and Developing Economies," Sustainability, MDPI, vol. 15(7), pages 1-19, March.
    9. Mateane, Lebogang, 2023. "Risk preferences, global market conditions and foreign debt: Is there any role for the currency composition of FX reserves?," Research in Economics, Elsevier, vol. 77(3), pages 402-418.
    10. Philippe Goulet Coulombe & Maximilian Gobel, 2023. "Maximally Machine-Learnable Portfolios," Working Papers 23-01, Chair in macroeconomics and forecasting, University of Quebec in Montreal's School of Management, revised Apr 2023.
    11. Cañon, Carlos & Gerba, Eddie & Pambira, Alberto & Stoja, Evarist, 2024. "An unconventional FX tail risk story," LSE Research Online Documents on Economics 125291, London School of Economics and Political Science, LSE Library.
    12. Xiaowei Zheng & Muhammad Faheem & Khusniddin Fakhriddinovch Uktamov, 2024. "Exploring the link between economic policy uncertainty, financial development, ecological innovation and environmental degradation; evidence from OECD countries," PLOS ONE, Public Library of Science, vol. 19(9), pages 1-25, September.
    13. Shuotao Diao & Suvrajeet Sen, 2024. "Distribution-free algorithms for predictive stochastic programming in the presence of streaming data," Computational Optimization and Applications, Springer, vol. 87(2), pages 355-395, March.
    14. Farhadi, Sajjad & Seresht, Hanieh Atrian & Aghakhani, Hamidreza & Baghapour, Behzad, 2025. "Performance prediction of heat pipe evacuated tube solar collectors: Analytical modeling and data-driven machine learning/ANN approach with developing web application," Energy, Elsevier, vol. 321(C).
    15. Tao Xiong & Miao Li & Jia Cao, 2023. "Do Futures Prices Help Forecast Spot Prices? Evidence from China’s New Live Hog Futures," Agriculture, MDPI, vol. 13(9), pages 1-16, August.
    16. Yu, Yue & Wang, Jianzhou & Jiang, He & Lu, Haiyan, 2025. "How to manage a multifactor-driven crude oil market more effectively? A revisit based on the multiple criteria perspective," Resources Policy, Elsevier, vol. 100(C).
    17. Sadana, Utsav & Chenreddy, Abhilash & Delage, Erick & Forel, Alexandre & Frejinger, Emma & Vidal, Thibaut, 2025. "A survey of contextual optimization methods for decision-making under uncertainty," European Journal of Operational Research, Elsevier, vol. 320(2), pages 271-289.
    18. Roche, Steven & Otarra, Carmela & Fell, Imogen & Belle Torres, Christine & Rees, Sydney, 2023. "Online sexual exploitation of children in the Philippines: A scoping review," Children and Youth Services Review, Elsevier, vol. 148(C).
    19. Zhai, Dongsheng & Zhang, Tianrui & Liang, Guoqiang & Liu, Baoliu, 2025. "Research on crude oil futures price prediction methods: A perspective based on quantum deep learning," Energy, Elsevier, vol. 320(C).
    20. Herve, Fabrice & Rouine, Ibtissem & Thraya, Mohamed Firas & Zouaoui, Mohamed, 2024. "Investor sentiment and M&A withdrawal: International evidence," International Review of Financial Analysis, Elsevier, vol. 96(PB).

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2604.12082. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.