Paper: arXiv 2507.15079
Authors: Arkadiusz Lipiecki, Bartosz Uniejewski
Abstract
Quantifying the uncertainty of forecasting models is essential to assess and mitigate the risks associated with data-driven decisions, especially in volatile domains such as electricity markets. Machine learning methods can provide highly accurate electricity price forecasts, critical for informing the decisions of market participants. However, these models often lack uncertainty estimates, which limits the ability of decision makers to avoid unnecessary risks. In this paper, we propose a novel method for generating probabilistic forecasts from ensembles of point forecasts, called Isotonic Quantile Regression Averaging (iQRA). Building on the established framework of Quantile Regression Averaging (QRA), we introduce stochastic order constraints to improve forecast accuracy, reliability, and computational costs. In an extensive forecasting study of the German day-ahead electricity market, we show that iQRA consistently outperforms state-of-the-art postprocessing methods in terms of both reliability and sharpness. It produces well-calibrated prediction intervals across multiple confidence levels, providing superior reliability to all benchmark methods, particularly coverage-based conformal prediction. In addition, isotonic regularization decreases the complexity of the quantile regression problem and offers a hyperparameter-free approach to variable selection.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper introduces a novel ‘Isotonic Quantile Regression Averaging’ (iQRA) method, building on established quantile regression frameworks with stochastic order constraints and regularization, indicating advanced mathematical formulation. Empirically, it includes a detailed 10-year study on the German day-ahead electricity market with specific data preprocessing, model architecture (NARX neural networks), rolling-window backtesting, and comparison against multiple state-of-the-art benchmarks using metrics like CRPS and ACE.
Research Flowchart
flowchart TD A["Research Goal: Quantify uncertainty<br>in electricity price forecasts"] --> B["Methodology: Isotonic Quantile<br>Regression Averaging iQRA"] B --> C["Data: German Day-Ahead<br>Electricity Market Forecasts"] C --> D["Process: Ensemble Point Forecasts<br>+ Stochastic Order Constraints"] D --> E["Computation:<br>Isotonic Regularization<br>Hyperparameter-Free Selection"] E --> F["Output: Probabilistic<br>Prediction Intervals"] F --> G["Key Findings:<br>Outperforms State-of-the-Art"] G --> H["Outcomes: Superior Reliability<br>& Sharpness across confidence levels"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper introduces Isotonic Quantile Regression Averaging (iQRA), a novel method for generating probabilistic forecasts from ensembles of point forecasts.
Source sentence
we propose a novel method for generating probabilistic forecasts from ensembles of point forecasts, called Isotonic Quantile Regression Averaging (iQRA).
Assumes 2
- The covariates used in post‑processing are point estimates of the target variable, justifying a stochastic order (isotonic) constraint. statistical
Source sentence
This assumption is clearly justified when the covariates are point estimates of the target
- The target variable (electricity price) is isotonic with respect to its point forecasts. statistical
Source sentence
the isotonicity assumption is at the core of a recently proposed isotonic distributional regression
Data
- German day‑ahead electricity prices market-prices public
Source sentence
The core of the dataset consists of day‑ahead electricity prices from the ENTSO‑E transparency platform
- Day‑ahead forecasts of system load, solar and wind generation fundamentals public
Source sentence
we included day‑ahead forecasts of system load, solar generation, and aggregated wind generation (onshore and offshore) in Germany, also from ENTSO‑E
- Commodity market indicators (coal, natural gas, crude oil, carbon allowances) macro public
Source sentence
closing prices of coal (API2), natural gas (TTF), crude oil (Brent) and carbon emission allowances (EUA) - sourced from Investing.com
Costs
Not applicable
Finds 2
- iQRA achieves the best prediction‑interval pinball score at the 98% confidence level and significantly outperforms all other competitors across all confidence levels. performance
Source sentence
The iQRA model delivers the best results for the 98% highlighting its strength
- Across five out‑of‑sample years, iQRA (and LQRA) consistently attain the lowest or near‑lowest continuous ranked probability scores. predictive-accuracy
Source sentence
iQRA and LQRA models consistently achieve the lowest or near‑lowes…
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 9 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive : The Evolution of Probabilistic Price Forecasting Techniques: …
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (64)
- PostForecasts.jl: A Julia package for probabilistic forecasting by postprocessing point predictions (2025) — link
- The Model Confidence Set (2011) — link
- Operational Research: methods and applications (2024)
- A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021)
- Value-oriented forecast reconciliation for renewables in electricity markets (2025)
- Energy Forecasting: A Review and Outlook (2020)
- Postprocessing of point predictions for probabilistic forecasting of day-ahead electricity prices: The benefits of using isotonic distributional regression — → 2404.02270
- On-line conformalized neural networks ensembles for probabilistic forecasting of day-ahead electricity prices (2025)
and 56 more
- Probabilistic forecasting of wind power ramp events using autoregressive logit models (2017)
- Probabilistic forecasting of wave height for offshore wind turbine maintenance (2018)
- Forecasting hourly electricity prices using ARMAX–GARCH models: An application to MISO hubs (2012)
- ARX-GARCH Probabilistic Price Forecasts for Diversification of Trade in Electricity Markets—Variance Stabilizing Transformation and Financial Risk-Minimizing Portfolio Allocation (2023)
- Forecasting electricity prices with expert, linear, and nonlinear models (2023)
- Conformal prediction interval estimation and applications to day-ahead and intraday power markets (2021)
- Adaptive Conformal Predictions for Time Series (2022)
- Distributional modeling and short-term forecasting of electricity prices by G eneralized A dditive M odels for Location, Scale and Shape (2011)
- Online Distributional Regression (2024) — link
- Distributional neural networks for electricity price forecasting (2023)
- Isotonic distributional regression (2021)
- Easy Uncertainty Quantification (EasyUQ): Generating Predictive Distributions from Single-Valued Model Output (2024)
- Monotone Percentile Regression (1976)
- About monotone regression quantiles (2000)
- Quantile regression with monotonicity restrictions using P-splines and the L1-norm (2006)
- Nonparametric Quantile Estimation (2006)
- Monotone least squares and isotonic quantiles (2020)
- Non-crossing nonlinear regression quantiles by monotone composite quantile regression neural network, with application to rainfall extremes (2018)
- Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark (2021)
- Probabilistic electricity price forecasting with NARX networks: Combine point or probabilistic forecasts? (2020)
- Day-ahead electricity price forecasting with high-dimensional structures: U nivariate vs. multivariate modeling frameworks (2018)
- Forecasting Electricity Prices (2023)
- A data-driven merit order: Learning a fundamental electricity price model — → 2501.02963
- Training feedforward networks with the Marquardt algorithm (1994)
- Computing electricity spot price prediction intervals using quantile regression and forecast averaging (2015)
- Smoothing quantile regression averaging: A new approach to probabilistic forecasting of electricity prices — → 2302.00411
- Regularized Quantile Regression Averaging for probabilistic electricity price forecasting (2021)
- Combining forecast quantiles using quantile regression: Investigating the derived weights, estimator bias and imposing constraints (1998)
- Probabilistic load forecasting via Q uantile R egression A veraging on sister forecasts (2017)
- Combining quantiles of calibrated solar forecasts from ensemble numerical weather prediction (2023)
- A probabilistic forecast methodology for volatile electricity prices in the Australian National Electricity Market (2024)
- A hybrid model for GEFCom2014 probabilistic electricity price forecasting (2016)
- Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting (2016)
- ProbCast: Open-source Production, Evaluation and Visualisation of Probabilistic Forecasts (2020)
- Smoothing Quantile Regressions (2021)
- Kernel Density Estimators (1992)
- Regression Shrinkage and Selection via the Lasso (1996)
- L1-Norm Quantile Regression (2008) — link
- Quantile regression via iterative least squares computations (2012)
- Strictly Proper Scoring Rules, Prediction, and Estimation (2007)
- Recent advances in electricity price forecasting: A review of probabilistic forecasting (2018)
- Combining predictive distributions of electricity prices. Does minimizing the CRPS lead to optimal decisions in day-ahead bidding? — → 2308.15443
- Tests of conditional predictive ability (2006)
- Statistical and economic evaluation of forecasts in electricity markets: Beyond RMSE and MAE — → 2511.13616
- Loss functions in regression models: Impact on profits and risk in day-ahead electricity trading (2025)
- Quantile Regression (2005)
- Parallelizing the dual revised simplex method (2018) — link
- Efficient Inverse Maintenance and Faster Algorithms for Linear Programming (2015)
- A Deterministic Linear Program Solver in Current Matrix Multiplication Time (2020)
- Algorithm 733: TOMP –Fortran modules for optimal control calculations (1994) — link
- The NLopt nonlinear-optimization package (2007)
- The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2009)
- Forecasting with trees (2022)
- XGBoost : A Scalable Tree Boosting System (2016) — link
- Optuna: A Next-generation Hyperparameter Optimization Framework (2019) — link
- Probabilistic forecasting with a hybrid Factor-QRA approach: Application to electricity trading — → 2303.08565
6 of 64 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.