{"paper_id":"2504.05743","title":"Causal Portfolio Optimization: Principles and Sensitivity-Based Solutions","authors":["Alejandro Rodriguez Dominguez"],"paper_date":"2025-04-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2504.05743v2","page_url":"https://thequant.space/flowcharts/causal-portfolio-optimization-principles-and-sensitivity-ba/","scores":{"empirical_rigor":3,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a novel risk management framework based on Common Causal Manifolds and introduces the Hierarchical Sensitivity Parity (HSP) portfolio optimization method.","quote":"Finally, the work introduces a novel risk management framework based on Common Causal Manifolds, including both theoretical development and experimental validation.","summary":"Fundamental and necessary principles for achieving efficient portfolio optimization based on asset and diversification dynamics are presented. The Commonality Principle is a necessary and sufficient condition for identifying optimal drivers of a portfolio in terms of its diversification dynamics.…","strategy":"Hierarchical Sensitivity Parity (HSP)"},"assumptions":{"status":"available","items":[{"assumption":"All portfolio constituents are generated by a shared set of common drivers (Markov Common Cause Principle).","type":"model","stated":"explicit","quote":"Specifically, we assume that all portfolio constituents 𝑎𝑖 are generated by a shared set of common drivers 𝑫, such that: 𝑎𝑖⊥𝑎𝑗| 𝑫"},{"assumption":"Linear regressions and Gaussian assumptions are used for conditional expectations.","type":"statistical","stated":"explicit","quote":"under Gaussian assumptions and linear conditional models, reduces to a function of the pairwise covariances"},{"assumption":"Driver selection relies on correlation analysis over historical windows.","type":"data","stated":"explicit","quote":"Driver selection is based on correlation analysis computed over 6-month or 12-month historical windows"},{"assumption":"Maximum allocation per asset is limited to 10% to prevent concentration.","type":"execution","stated":"explicit","quote":"Constraints are imposed to ensure practical weight distributions, such as a maximum allocation of 10% per asset"}]},"datasets":{"status":"available","items":[{"name":"Bloomberg dataset","provider":"Bloomberg","kind":"market-prices","access":"commercial","period":"2012-2021","universe":"global FX crosses, government bonds, macro indicators, equity indices, mutual fund indices","quote":"The first dataset includes approximately 1200 time series spanning from 2012 to the end of 2021. It comprises: – Spot and option prices","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"9.1 Implementation The data used in the implementation is sourced from Bloomberg and is organized into two primary datasets stored in a structured database: • The first dataset includes approximately 1200 time series spanning from 2012 to the end of 2021.","mentions":1,"used_in":1}],"sample":{"start":"2020-06","end":"2021-12","market":"U.S. stocks","asset_class":"equities","frequency":"monthly"},"data_resolution":"unclear"},"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 Hierarchical Sensitivity Parity (HSP) variants achieve higher returns (≈49‑50%) and Sharpe ratios (~3.0) than standard mean‑variance and equally weighted benchmarks over the period 01/06/2020‑01/12/2021.","kind":"performance","quote":"Table 4: USA portfolio performance metrics for top mean-variance methods and 1/N: Returns, Risks, and Sharpes for full period: 01/06/2020 – 01/12/2021"}],"reported_performance":{"strategy":"Hierarchical Sensitivity Parity (HSP)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":55,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":8,"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":"2026-11-14T17:41:14Z"},"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/"}