{"paper_id":"2308.15443","title":"Combining predictive distributions of electricity prices: Does minimizing the CRPS lead to optimal decisions in day-ahead bidding?","authors":["Weronika Nitka","Rafał Weron"],"paper_date":"2023-08-29","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.15443v1","page_url":"https://thequant.space/flowcharts/combining-predictive-distributions-of-electricity-prices-do/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using CRPS learning, a weighting technique that minimizes the continuous ranked probability score, to combine probabilistic electricity price forecasts and assess its impact on day-ahead bidding decisions.","quote":"In this article we address the question of whether using CRPS learning, a novel weighting technique minimizing the continuous ranked probability score (CRPS), leads to optimal decisions in day-ahead bidding.","summary":"Probabilistic price forecasting has recently gained attention in power trading because decisions based on such predictions can yield significantly higher profits than those made with point forecasts alone. At the same time, methods are being developed to combine predictive distributions, since no…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A standard short-term forecast horizon of 1 day, performed in a rolling window scheme.","type":"model","stated":"explicit","quote":"We assume a standard short-term forecast horizon of 1 day, performed in a rolling window scheme"},{"assumption":"Forecasts of all 24 hourly prices on day d are calculated in the morning of day d‑1, before the day‑ahead market closes.","type":"execution","stated":"explicit","quote":"We assume that forecasts of all 24 hourly prices on day d are calculated at the same time in the morning of day d −1, i.e., before the day-ahead market for day d closes"},{"assumption":"Model parameters are estimated using a calibration sample of the D most recent past observations.","type":"model","stated":"explicit","quote":"the model parameters are estimated using a calibration sample of D most recent past observations"},{"assumption":"Battery charging and discharging efficiency is 90%.","type":"execution","stated":"explicit","quote":"We assume that the efficiency of charging as well as discharging the battery is 90%"},{"assumption":"Total usable battery capacity is 2 MWh and it starts half‑charged at the beginning of the simulation.","type":"execution","stated":"explicit","quote":"we assume that the total usable capacity of the battery is B = 2 MWh and that at the beginning of the simulation period the battery starts halfway charged (B = 1)"}]},"datasets":{"status":"available","items":[{"name":"German EPEX day‑ahead electricity prices","provider":"ENTSO‑E Transparency platform","kind":"market-prices","access":"public","period":"1 January 2015 to 31 December 2020","universe":"German day‑ahead market","quote":"hourly day-ahead electricity prices from the German EPEX market spanning the period from 1 January 2015 to 31 December 2020"},{"name":"Load and RES generation forecasts","provider":"ENTSO‑E Transparency platform","kind":"fundamentals","access":"public","period":"1 January 2015 to 31 December 2020","universe":"German market","quote":"prices as well as the day-ahead predictions of the loads and RES generation are publicly available from the ENTSO‑E Transparency platform"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Increasing the diversity of an ensemble positively impacts forecast accuracy.","kind":"predictive-accuracy","quote":"We find that increasing the diversity of an ensemble can have a positive impact on accuracy."},{"finding":"CRPS learning yields slightly better predictions on average, but does not lead to higher profits despite higher accuracy.","kind":"negative","quote":"higher computational cost of using CRPS learning compared to an equal-weighted aggregation of distributions is not offset by higher profits, despite significantly more accurate predictions."},{"finding":"The DDNN_JSU_CRPS_LEAR ensemble achieves the lowest CRPS score among all models and ensembles.","kind":"predictive-accuracy","quote":"The DDNN_JSU_CRPS_LEAR ensemble achieves the lowest CRPS score."},{"finding":"CRPS learning yields slightly better predictions on average compared to equal weighting.","kind":"predictive-accuracy","quote":"Nevertheless, CRPS learning yields slightly better predictions on average."},{"finding":"Introducing diversity to a pool of forecasts is highly beneficial for both forecast accuracy (CRPS) and trading profits in the German day‑ahead market.","kind":"performance","quote":"introducing diversity to a pool of forecasts is highly beneficial, both in terms of forecast accuracy measured by the CRPS and profits from a trading strategy implemented in the German day-ahead power market"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2506.21246","title":"From On-chain to Macro: Assessing the Importance of Data Source Diversity in Cryptocurrency Market Forecasting","paper_date":"2025-06-26","authors":["Giorgos Demosthenous","Chryssis Georgiou","Eliada Polydorou"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/from-on-chain-to-macro-assessing-the-importance-of-data-sou/"},"question":"Does increasing diversity (ensemble or data sources) improve forecasting accuracy?","this_paper_finding":"Increasing the diversity of an ensemble positively impacts forecast accuracy.","other_paper_finding":"Data source diversity significantly enhances forecasting model performance across time horizons.","other_paper_quote":"Our comprehensive experiments demonstrate that data source diversity significantly enhances the predictive performance of forecasting models across different time horizons.","note":"Both findings report a positive impact of diversity on forecast performance; A focuses on electricity price ensembles, B on cryptocurrency data sources.","confidence":0.521}],"contradicts":[{"paper":{"paper_id":"2611.17170","title":"Improving Algorithmic Trading for BESS on Intraday Electricity Markets through Distributional Price Forecasts","paper_date":"2026-11-12","authors":["Simon Hirsch","David Schaurecker","David Wozabal"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/improving-algorithmic-trading-for-bess-on-intraday-electricity-markets-through/"},"question":"Does higher predictive accuracy of electricity price forecasts translate into higher trading profits for BESS?","this_paper_finding":"CRPS learning yields slightly better predictions on average, but does not lead to higher profits despite higher accuracy.","other_paper_finding":"Forecast errors and instability are strongly negatively correlated with daily profits, indicating predictive accuracy drives returns.","other_paper_quote":"a strong negative correlation between error metrics, forecast stability, and daily profits, indicating that predictive accuracy is a driving factor in returns.","note":"A finds CRPS improves accuracy but not profits; B finds forecast errors negatively correlate with daily profits, showing accuracy drives returns.","confidence":0.402}],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":5,"by_independent_authors":4,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":1,"mentions":2,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2604.19580","title":"Probabilistic Forecasting for Day-ahead Electricity Prices, Battery Trading Strategies and the Economic Evaluation of Predictive Accuracy","paper_date":"2026-04-21","authors":["Simon Hirsch","Florian Ziel"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/probabilistic-forecasting-for-day-ahead-electricity-prices-battery-trading/"},"how":"discusses_findings","quote":"we see that measures of decision quality and scoring rules disagree also in the probabilistic setting."},{"paper":{"paper_id":"2507.15079","title":"Isotonic Quantile Regression Averaging for uncertainty quantification of electricity price forecasts","paper_date":"2025-07-20","authors":["Arkadiusz Lipiecki","Bartosz Uniejewski"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/isotonic-quantile-regression-averaging-for-uncertainty-quant/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:22:58Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}