{"paper_id":"2510.20434","title":"Market-Implied Sustainability: Insights from Funds' Portfolio Holdings","authors":["Rosella Giacometti","Gabriele Torri","Marco Bonomelli","Davide Lauria"],"paper_date":"2025-10-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.20434v1","page_url":"https://thequant.space/flowcharts/market-implied-sustainability-insights-from-funds-portfoli/","scores":{"empirical_rigor":7,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a framework to construct Market‑Implied Sustainability (MIS) scores for individual firms using fund‑level sustainability classifications and granular portfolio holdings.","quote":"In this work we propose a framework to construct Market‑Implied Sustainability (MIS) scores for individual firms by exploiting fund‑level sustainability classifications and granular portfolio holdings.","summary":"In this work, we aim to develop a market-implied sustainability score for companies, based on the extent to which a stock is over- or under-represented in sustainable funds compared to traditional ones. To identify sustainable funds, we rely on the Sustainable Finance Disclosure Regulation (SFDR)…","strategy":"Top MIS max‑Sharpe portfolio"},"assumptions":{"status":"available","items":[{"assumption":"Long‑only positions are assumed for the MIS indicator.","type":"model","stated":"explicit","quote":"Assuming long‑only positions, the indicator is bounded between −1 and 1, with positive values denoting assets that are over‑represented in the funds labelled as sustainable"},{"assumption":"SFDR fund classifications are taken from a single revision (2023) and applied retrospectively to the whole sample.","type":"data","stated":"explicit","quote":"we adopt the classification in a single period, while explicitly discussing the implications of this retrospective assumption"},{"assumption":"MIS scores are computed quarterly.","type":"execution","stated":"explicit","quote":"MIS scores for a large cross‑section of European companies over the period 2010–2025"}]},"datasets":{"status":"available","items":[{"name":"Historical portfolio holdings","provider":"Lipper (provided by LSEG)","kind":"fundamentals","access":"commercial","period":"2010–2025","universe":"≈500 European equity mutual funds and ETFs","quote":"The construction of MIS scores relies on a dataset of historical portfolio holdings for a panel of approximately 500 equity mutual funds and ETFs with a geographic focus on Europe. The portfolio holding data are issued by Lipper and provided by LSEG. The sample covers the period 2010–2025 at a quarterly frequency.","known_id":"refinitiv"},{"name":"LSEG ESG scores","provider":"LSEG plc","kind":"fundamentals","access":"commercial","period":"2010–2025","universe":"European companies in the holdings dataset","quote":"with firm‑level ESG ratings provided by LSEG plc, a widely used benchmark in the literature.","known_id":"refinitiv"},{"name":"Daily share price data","provider":"LSEG Workspace","kind":"other","access":"commercial","period":"2010–2025","universe":"European stocks in the sample","quote":"For each stock, we retrieve from LSEG Workspace the daily share price, the annual ESG score, and a set of corporate...","known_id":"refinitiv"}],"known":[{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"We then examine how MIS relates to traditional firm-level ESG ratings provided by LSEG and analyze the determinants of potential divergences between the two measures.","mentions":34,"used_in":14}],"sample":{"start":"2010","end":"2023","market":"European stocks","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"All reported performance measures are net of transaction costs.","quote":"all reported performance measures are net of transaction costs.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"All reported performance measures are net of transaction costs.","card_quote":"all reported performance measures are net of transaction costs.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"MIS scores capture dimensions of sustainability that differ systematically from conventional ESG ratings.","kind":"statistical","quote":"The results show that MIS scores capture dimensions of sustainability that differ systematically from conventional ESG ratings."},{"finding":"Tilting portfolios toward firms with high MIS scores improves risk‑adjusted performance, while ESG‑based strategies do not deliver comparable gains.","kind":"performance","quote":"In portfolio applications, tilting toward firms with high MIS scores improves risk‑adjusted performance, whereas strategies based solely on ESG ratings do not deliver comparable gains."},{"finding":"Risk measures of MIS‑based tilting strategies are statistically significant and lie outside the 90% confidence interval of random benchmarks.","kind":"statistical","quote":"The differences in risk measures are statistically significant, as they fall outside the confidence intervals derived from the random strategies."},{"finding":"High‑MIS portfolios show lower risk and comparable or higher returns relative to synthetic index and random portfolios.","kind":"performance","quote":"... “Top MIS” and “Bottom ESG–Top MIS” exhibit the strongest out‑of‑sample performance, characterized by lower risk relative to both the synthetic index and the random portfolios."}],"reported_performance":{"strategy":"Top MIS max‑Sharpe portfolio","sharpe":0.35,"sharpe_benchmark":0.16,"annual_return_pct":5.95,"total_return_pct":null,"max_drawdown_pct":2.64},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":55,"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":"2026-11-14T17:23:48Z"},"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/"}