{"paper_id":"2306.08105","title":"Model-Free Market Risk Hedging Using Crowding Networks","authors":["Vadim Zlotnikov","Jiayu Liu","Igor Halperin","Fei He","Lisa Huang"],"paper_date":"2023-06-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.08105v1","page_url":"https://thequant.space/flowcharts/model-free-market-risk-hedging-using-crowding-networks/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes using graph eigenvector centrality to compute crowding scores for stocks and construct a model‑free, costless long‑short hedge portfolio without numerical optimization.","quote":"These scores are used to construct costless long-short portfolios, computed in a distribution-free (model-free) way and without using any numerical optimization, with desirable properties of hedge portfolios.","summary":"Crowding is widely regarded as one of the most important risk factors in designing portfolio strategies. In this paper, we analyze stock crowding using network analysis of fund holdings, which is used to compute crowding scores for stocks. These scores are used to construct costless long-short…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Fund holdings data are only available about 45 days after the quarter end.","type":"data","stated":"explicit","quote":"Considering that fund holdings data is only available about 45 days after the quarter end, we construct the portfolios 2 months after the quarter end."},{"assumption":"Portfolios are constructed 2 months after quarter end and evaluated over the next 1, 3, 6, and 12 months.","type":"execution","stated":"explicit","quote":"Considering that fund holdings data is only available about 45 days after the quarter end, we construct the portfolios 2 months after the quarter end. We observe the returns for the next 1, 3, 6, and 12 months."},{"assumption":"Factor exposures are limited to between -0.02 and 0.02 for beta, growth, momentum, volatility and size.","type":"model","stated":"explicit","quote":"we use a proprietary optimizer to limit factors exposure between -0.02 and 0.02 for the following Tive Barra factors: beta, growth, momentum, volatility and size."},{"assumption":"The long‑short portfolio construction relies only on linear algebra and does not use any optimization.","type":"model","stated":"explicit","quote":"construction of our long‑short portfolio does not rely on any optimization and uses only linear algebra."},{"assumption":"The total cost of hedging equals the total cost of rebalancing the hedge portfolio.","type":"execution","stated":"explicit","quote":"The total cost of such hedging amounts to the total cost of rebalancing the hedge portfolio."}]},"datasets":{"status":"available","items":[{"name":"13F fund holdings reports","provider":"SEC","kind":"alternative","access":"public","period":null,"universe":null,"quote":"…d hedge funds in 13F reports. The crowding signals were further used to construct a diversiTied portfolio that has desired characteristics during periods of market downturns."},{"name":"Russell 1000 market returns","provider":"FTSE Russell","kind":"market-prices","access":"public","period":null,"universe":"Russell 1000","quote":"correlation with the market returns (Russell 1000)"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"partial","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"Costs are assumed to equal the rebalancing costs of the hedge portfolio; no explicit cost figures are provided.","card_quote":"The total cost of such hedging amounts to the total cost of rebalancing the hedge portfolio.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Stocks with higher eigenvector centrality (more crowded) underperform less crowded stocks on average.","kind":"performance","quote":"On average the most crowded quintile underperforms the less crowded quintiles with a s…"},{"finding":"The long‑short crowding portfolio provides protection for both small and large market price fluctuations, showing negative correlation with the market and positive convexity.","kind":"performance","quote":"More specifically, these long-short portfolios provide protection for both small and large market price fluctuations, due to their negative correlation with the market and positive convexity as a function of market returns."},{"finding":"Adding the crowding‑based long‑short hedge to a baseline 60/40 portfolio offers an alternative way to hedge tail risk without costly option‑based strategies.","kind":"performance","quote":"By adding our long-short portfolio to a baseline portfolio such as a traditional 60/40 portfolio, our method provides an alternative way to hedge portfolio risk including tail risk, which does not require costly option-based strategies or complex numerical optimization."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2512.11913","title":"Not All Factors Crowd Equally: Modeling, Measuring, and Trading on Alpha Decay","paper_date":"2025-12-11","authors":["Chorok Lee"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/not-all-factors-crowd-equally-modeling-measuring-and-trad/"},"question":"Does crowding predict tail risk and can it be used for hedging?","this_paper_finding":"Adding the crowding‑based long‑short hedge to a baseline 60/40 portfolio offers an alternative way to hedge tail risk without costly option‑based strategies.","other_paper_finding":"Average returns are efficiently priced; crowding predicts tail risk rather than mean returns.","other_paper_quote":"Average returns are efficiently priced. Crowding","note":"Both findings agree that crowding predicts tail risk rather than mean returns; A adds a crowding‑based hedge, B confirms the predictive power.","confidence":0.732}],"contradicts":[],"qualifies":[],"compared_with":10,"citations":{"cited_by_in_corpus":2,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"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":"2026-11-14T18:25:52Z"},"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/"}