{"paper_id":"2503.20987","title":"A Causal Perspective of Stock Prediction Models","authors":["Songci Xu","Qiangqiang Cheng","Chi-Guhn Lee"],"paper_date":"2025-03-26","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2503.20987v1","page_url":"https://thequant.space/flowcharts/a-causal-perspective-of-stock-prediction-models/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel error bound that explicitly incorporates causality from multi‑factor models and introduces a Causal Discovery technique to learn invariant feature representations that reduce this error bound.","quote":"ii. We develop the Causal Discovery technique to learn invariant feature representations that reduces the proposed error bound, whose influence from spurious correlations are also rigorously analyzed.","summary":"In the realm of stock prediction, machine learning models encounter considerable obstacles due to the inherent low signal-to-noise ratio and the nonstationary nature of financial markets. These challenges often result in spurious correlations and unstable predictive relationships, leading to poor…","strategy":"Causal Discovery with K=4"},"assumptions":{"status":"available","items":[{"assumption":"For all T>0 and τ>0, the minima of the set {P(JT′ > τ) | T′ ≥T} exist.","type":"other","stated":"explicit","quote":"Assumption 3.1: ∀T > 0 and ∀τ > 0, the minima of the set {P(JT ′ > τ) | T ′ ≥T} exist."}]},"datasets":{"status":"available","items":[{"name":"Chinese A‑share market","provider":null,"kind":"market-prices","access":"public","period":"2010-01-04 to 2024-03-04","universe":"≈4000 stocks, top 1000 by market cap selected daily","quote":"We present a comprehensive analysis of the Chinese A‑share market over the period from January 4, 2010, to March 4, 2024, encompassing more than 4000 stocks."},{"name":"Alpha191 dataset","provider":"GUOTAI JUNAN SECURITIES","kind":"alternative","access":"commercial","period":null,"universe":null,"quote":"The Alpha191 dataset, provided by GUOTAI JUNAN SECURITIES, consists of 191 quantitative 1‑dimensional signals tailored for the Chinese market, each representing a distinct formula based on various market data such as prices and volumes."}],"known":[],"sample":{"start":"2022-09","end":"2024-03","market":"stock universe","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"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":"Causal discovery algorithms (˜K ≥1) consistently outperform baseline models in both Sharpe Ratio and CAGR across all architectures and sub‑periods.","kind":"performance","quote":"Regardless of architectures or subperiods, the causal discovery algorithms (i.e., ˜K ≥1) outperform the baseline algorithms in terms of both SR and CAGR."},{"finding":"Increasing the number of causal discovery components improves performance, with ˜K = 4 achieving the highest SR (2.04) and CAGR (7.22%).","kind":"performance","quote":"˜K = 1: SR = 1.64, CAGR = 6.04%; ˜K = 2: SR = 1.91, CAGR = 6.88%; ˜K = 3: SR = 1.88, CAGR = 6.66%; ˜K = 4: SR = 2.04, CAGR = 7.22%."},{"finding":"Ensembling model outputs over multiple runs and architectures shows that ˜K ≥2 significantly outperforms ˜K = 1, and ˜K = 4 yields the best Sharpe Ratio and CAGR.","kind":"performance","quote":"Figure 1 shows the equity curves induced by the ensembled outputs, demonstrating that ˜K ≥2 significantly outperforms ˜K = 1, and ˜K = 4 results in the best SR and CAGR."}],"reported_performance":{"strategy":"Causal Discovery with K=4","sharpe":2.04,"sharpe_benchmark":null,"annual_return_pct":7.22,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"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":"2026-11-14T17:41:40Z"},"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/"}