{"paper_id":"2408.03320","title":"Hedge Fund Portfolio Construction Using PolyModel Theory and iTransformer","authors":["Siqiao Zhao","Zhikang Dong","Zeyu Cao","Raphael Douady"],"paper_date":"2024-08-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2408.03320v3","page_url":"https://thequant.space/flowcharts/hedge-fund-portfolio-construction-using-polymodel-theory-and/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes combining PolyModel theory with the iTransformer deep learning model to select hedge funds and construct high‑return, low‑risk portfolios.","quote":"we proposed the combination of PolyModel theory and iTransformer for hedge funds selection; the proposed strategies achieved much higher returns than the standard fund of fund benchmarks.","summary":"When constructing portfolios, a key problem is that a lot of financial time series data are sparse, making it challenging to apply machine learning methods. Polymodel theory can solve this issue and demonstrate superiority in portfolio construction from various aspects. To implement the PolyModel…","strategy":"simple average portfolio (SA)"},"assumptions":{"status":"available","items":[{"assumption":"The noise term ϵj has zero mean and is usually assumed to follow a normal distribution.","type":"statistical","stated":"explicit","quote":"ϵj is the noise term in the regression model with zero mean; usually it is assumed to be normal distribution but does not have to be."},{"assumption":"Each regression function Φij(x) is approximated by a polynomial of degree up to 4 using Hermite polynomials.","type":"model","stated":"explicit","quote":"where Hk(x) is the Hermitian polynomial of degree k."},{"assumption":"A polynomial of degree 4 is sufficiently flexible to capture the essential nonlinear relationship while keeping overfitting bearable.","type":"model","stated":"explicit","quote":"Based on authors’ practical experience, a polynomial of degree of 4 is flexible enough to capture nonlinear but essential relation between target and risk factor while usually suffer bearable overfitting."},{"assumption":"At each time stamp the analysis uses only the past three years of return data to compute a dynamic p‑value score.","type":"data","stated":"explicit","quote":"at each time stamp, we only look at the past 3 years’ return data, and thus, we can have a dynamic P-Value Score series for each target asset Yi and risk factor Xj pair."},{"assumption":"Features such as SVaR and LTS are computed using the past 36 months of data for the next month’s prediction.","type":"data","stated":"explicit","quote":"we use the past 36 months data to compute features such as SVaR and LTS for the next month’s pred…"},{"assumption":"The asset pool consists of over 10,000 hedge funds spanning roughly 29 years.","type":"data","stated":"explicit","quote":"utilizing over 10,000 hedge funds for the past 29 years’ data."}]},"datasets":{"status":"available","items":[{"name":"Hedge fund return dataset","provider":null,"kind":"macro","access":"unknown","period":"April 1994 to May 2023","universe":"over 10,000 hedge funds","quote":"The data sets cover a long period from April 1994 to May 2023."},{"name":"Risk factor dataset","provider":null,"kind":"macro","access":"unknown","period":null,"universe":"hundreds of risk factors from equities, coupons, bonds, industrial indexes, etc.","quote":"our study incorporates an extensive universe comprising hundreds of risk factors from different domains, including equities, coupons, bonds, industrial indexes, and more."}],"known":[],"sample":{"start":"1994-04","end":null,"market":null,"asset_class":"multi-asset","frequency":"monthly"},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The constructed strategies achieve better Sharpe ratio and annualized return than benchmarks.","kind":"performance","quote":"our strategies achieve better Sharpe ratio and annualized return."},{"finding":"Strategy SA delivers the highest cumulative return, while WA is more stable with less drawdown; both outperform benchmark indices significantly.","kind":"performance","quote":"SA has the best performance regarding the cumulative return; WA is more stable and suffers much less drawdown than SA. Both strategies outperform the benchmarks significantly."},{"finding":"The proposed combination of PolyModel features and iTransformer yields substantially higher returns than standard fund‑of‑fund benchmarks.","kind":"performance","quote":"the proposed strategies achieved much higher returns than the standard fund of fund benchmarks."}],"reported_performance":{"strategy":"simple average portfolio (SA)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":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":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"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":"2026-11-14T18:04:45Z"},"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/"}