{"paper_id":"2406.05094","title":"Investigating the price determinants of the European Emission Trading System: a non-parametric approach","authors":["Cristiano Salvagnin","Aldo Glielmo","Maria Elena De Giuli","Antonietta Mira"],"paper_date":"2024-06-07","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2406.05094v1","page_url":"https://thequant.space/flowcharts/investigating-the-price-determinants-of-the-european-emissio/","scores":{"empirical_rigor":7,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a non‑parametric approach using the Information Imbalance measure, combined with Gaussian Process regression, for mixed‑frequency nowcasting and forecasting of EU ETS prices.","quote":"We propose the use of the Information Imbalance, a recently introduced non‑parametric measure quantifying the degree to which a set of variables is informative with respect to another one, to study the relationships among macroeconomic, economic, uncertainty, and energy variables concerning EU ETS prices.","summary":"The European carbon market plays a pivotal role in the European Union’s ambitious target of achieving carbon neutrality by 2050. Understanding the intricacies of factors influencing European Union Emission Trading System (EU ETS) market prices is paramount for effective policy making and strategy…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The Gaussian Process mean function is assumed to be zero.","type":"model","stated":"explicit","quote":"Without loss of generality, the GP mean function is typically assumed to be zero as the GP is typically applied to standardised data."},{"assumption":"A smoothness parameter ν is set to 1.5, the largest degree of smoothness compatible with all the time series available.","type":"model","stated":"explicit","quote":"In all our experiments, we set the smoothness parameter, ν, to 1.5, the largest degree of smoothness compatible with all the time series available"},{"assumption":"Mixed‑frequency data can be aggregated using Gaussian Processes with a low noise level σ²_n = 10⁻³ for regularisation.","type":"data","stated":"explicit","quote":"a GP is fit to the data using a low noise level of σ2 n = 10−3 just needed to regularise the inversion in Eq. 4, and the posterior GP mean is then used to compute the value of the time series at the needed"},{"assumption":"Information Imbalance does not depend on any model assumptions about the underlying time series relationships.","type":"statistical","stated":"explicit","quote":"Unlike conventional parametric econometric models, the Information Imbalance does not depend on any assumption on the model behind the time series and their relationships."}]},"datasets":{"status":"available","items":[{"name":"EUA (EUA) price series","provider":"Bloomberg®","kind":"market-prices","access":"commercial","period":"January 2014 - April 2023","universe":null,"quote":"EUA (EUA) January 2014 - April 2023 Bloomberg®","known_id":"bloomberg"},{"name":"ERIX index","provider":"Bloomberg®","kind":"other","access":"commercial","period":"January 2014 - April 2023","universe":null,"quote":"ERIX index January 2014 - April 2023 Bloomberg®","known_id":"bloomberg"},{"name":"Euro-area GDP (current value)","provider":"Eurostat","kind":"macro","access":"public","period":"January 2014 - April 2023","universe":null,"quote":"Euro-area GDP (current value) January 2014 - April 2023 Eurostat"},{"name":"Euro-area inflation (HICP)","provider":"Eurostat","kind":"macro","access":"public","period":"January 2014 - April 2023","universe":null,"quote":"Euro-area inflation (HICP) January 2014 - April 2023 Eurostat"},{"name":"Uncertainty EUR/CHF (CAFZUECH)","provider":"Bloomberg®","kind":"other","access":"commercial","period":"January 2014 - April 2023","universe":null,"quote":"Uncertainty EUR/CHF (CAFZUECH) January 2014 - April 2023 Bloomberg®","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"Data We collect daily closing prices of EUA from Bloomberg®, spanning from January 2014 to April 2023.","mentions":28,"used_in":2}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"In Phase 3 the most informative variables are the ERIX index, EUROSTOXX Electricity index and the 3‑month bond yield.","kind":"statistical","quote":"ERIX index, EUROSTOXX Electricity index, 3-month Bond yield were the top 3 most informative variables for Phase 3."},{"finding":"In Phase 4 the most informative variables are uncertainty on the EUR/CHF exchange rate, coal prices and the EUR/USD spot rate.","kind":"statistical","quote":"For Phase 4, the most informative variables include Uncertainty on EUR/CHF exchange rate, Coal prices, and EUR/USD Spot rate."},{"finding":"Commodity‑related variables are highly correlated with EUA price in Phase 3, while uncertainty‑related variables are poorly correlated in Phase 3 but become more positively correlated in Phase 4.","kind":"statistical","quote":"during Phase 3, the uncertainty-related variables are poorly correlated with the target variable. Especially during Phase 4 most of the considered variables have a positive correlation"},{"finding":"The Information Imbalance approach identifies weekly frequency as the most informative time scale for predicting EU ETS prices.","kind":"statistical","quote":"we identify the weekly time scale as the most informative for predicting the EU ETS price."},{"finding":"Combining Information Imbalance with Gaussian Process regression enables efficient nowcasting and forecasting using very small sets of highly informative predictors.","kind":"performance","quote":"Finally, we show how the Information Imbalance can be effectively combined with Gaussian Process regression for efficient nowcasting and forecasting using very small sets of highly informative predictors."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":19,"citations":{"cited_by_in_corpus":3,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":2},"independent_papers":[],"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":"2026-11-14T18:08:11Z"},"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/"}