{"paper_id":"2312.10739","title":"Managing ESG Ratings Disagreement in Sustainable Portfolio Selection","authors":["Francesco Cesarone","Manuel Luis Martino","Federica Ricca","Andrea Scozzari"],"paper_date":"2023-12-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2312.10739v1","page_url":"https://thequant.space/flowcharts/managing-esg-ratings-disagreement-in-sustainable-portfolio-s/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a nonlinear three‑criteria portfolio optimization model that is reformulated as a convex quadratic program using a k‑sum optimization strategy.","quote":"We propose a nonlinear optimization model for our three-criteria portfolio selection problem. We show that it can be reformulated as an equivalent convex quadratic program by exploiting a technique known in the literature as the k-sum optimization strategy.","summary":"Sustainable Investing identifies the approach of investors whose aim is twofold: on the one hand, they want to achieve the best compromise between portfolio risk and return, but they also want to take into account the sustainability of their investment, assessed through some Environmental, Social…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"There are n risky assets and m rating agencies, each providing an ESG measure on a bounded real scale.","type":"data","stated":"explicit","quote":"Assume that there are n risky assets and m different rating agencies and that each agency evaluates the sustainability of each asset according to its own method and producing its ESG measure, which is a real number ranging between a minimum and a maximum value."},{"assumption":"The ESG scores from different agencies can be standardized to a common scale.","type":"model","stated":"explicit","quote":"To address this problem, the first step is to standardize the data."},{"assumption":"The ε‑constraint approach can be applied to the three‑objective portfolio selection model.","type":"model","stated":"implied","quote":"In view of Theorem 1, we apply the ε‑constraint approach to our original three‑objective portfolio selection model (12) by considering σ2P (x) as the objective function."}]},"datasets":{"status":"available","items":[{"name":"EuroStoxx50","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"EuroStoxx50 constituents","quote":"In the following tables we provide the computational results obtained in the application of our model (13) to the EuroStoxx50 and NASDAQ100 data sets"},{"name":"NASDAQ100","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"NASDAQ100 constituents","quote":"In the following tables we provide the computational results obtained in the application of our model (13) to the EuroStoxx50 and NASDAQ100 data sets"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"The proposed ESG‑aware optimization method outperforms standard portfolio selection methods and a single‑agency approach.","kind":"performance","quote":"the results show that our new method outperforms the others."},{"finding":"The k‑Worst NonESG model exhibits the highest out‑of‑sample VaR5 loss among the tested strategies.","kind":"negative","quote":"The only weakness of our models is related to the maximum out‑of‑sample loss measured by index VaR5 which for “Sust 4 kWorst” is the highest."},{"finding":"The approach is versatile, effective and computationally tractable for ESG‑inclusive portfolio selection.","kind":"other","quote":"Globally it is versatile, effective and computationally tractable."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"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":"2026-11-14T18:17:46Z"},"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/"}