{"paper_id":"2502.05218","title":"FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction","authors":["Yitong Duan","Weiran Wang","Jian Li"],"paper_date":"2025-02-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.05218v1","page_url":"https://thequant.space/flowcharts/factorgcl-a-hypergraph-based-factor-model-with-temporal-res/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes FactorGCL, a hypergraph-based factor model with temporal residual contrastive learning that mines hidden factors to improve stock return prediction.","quote":"we propose a hypergraph-based factor model with temporal residual contrastive learning (FactorGCL) that employs a hypergraph structure to better capture high-order nonlinear relationships among stock returns and factors.","summary":"As a fundamental method in economics and finance, the factor model has been extensively utilized in quantitative investment. In recent years, there has been a paradigm shift from traditional linear models with expert-designed factors to more flexible nonlinear machine learning-based models with…","strategy":"FactorGCL"},"assumptions":{"status":"available","items":[{"assumption":"The dataset is split temporally into training, validation, and test sets with a 5‑year, 1‑year, 2‑year split.","type":"data","stated":"explicit","quote":"We follow the temporal order to split the dataset into training set, validation set and test set, where the time length is 5 years : 1 year : 2 years"},{"assumption":"Secondary industry factors (83 industries) are used as prior factors with binary exposures.","type":"model","stated":"explicit","quote":"We adopt secondary industry factors as the prior factors (83 industries, if a stock belongs to the industry, the value of corresponding factor exposure is 1, otherwise 0)."},{"assumption":"Transaction costs are set to 0.3% in the investment simulation.","type":"execution","stated":"explicit","quote":"set TopK = 30, ∆t = 10, and the transaction cost to 0.3%."}]},"datasets":{"status":"available","items":[{"name":"China A‑shares market dataset","provider":null,"kind":"market-prices","access":"unknown","period":"01/01/2014 to 06/30/2023","universe":"5028 China A‑shares stocks","quote":"We conduct our experiments on the China A‑shares market, utilizing a dataset spanning from 01/01/2014 to 06/30/2023. This dataset includes 5028 stocks, excluding suspended or otherwise abnormal stocks, and is constructed from a sequence of market data comprising day‑level price‑volume data"},{"name":"CSI300 benchmark portfolio","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":null,"quote":"We use the equally weighted CSI300 and CSI500 portfolio as the benchmark"},{"name":"CSI500 benchmark portfolio","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":null,"quote":"We use the equally weighted CSI300 and CSI500 portfolio as the benchmark"}],"known":[],"sample":{"start":"2020-01","end":"2023-06","market":"CSI 300 and CSI 500 stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"partial","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"transaction cost set to 0.3% per trade in the back‑test","card_quote":"set TopK = 30, ∆t = 10, and the transaction cost to 0.3%.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"FactorGCL achieves the highest information coefficient (IC) and information‑ratio (ICIR) among all compared methods on the test dataset.","kind":"predictive-accuracy","quote":"Our method achieves the highest IC and ICIR among all the compared methods."},{"finding":"In investment simulations, FactorGCL outperforms all baselines across annualized return, information ratio, and return‑over‑maximum‑drawdown metrics.","kind":"performance","quote":"The investment simulation results show that our method achieves the best performance across all metrics, indicating that our model can achieve profitable investments in the real market."},{"finding":"Ablation studies confirm that removing any module (prior beta, hidden beta, etc.) degrades performance, validating the contribution of each component.","kind":"statistical","quote":"To verify the effectiveness of different modules in our framework, we build four variants of proposed model by removing the prior beta module, hid…"}],"reported_performance":{"strategy":"FactorGCL","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"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":21,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":3,"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":"2026-11-14T17:45:56Z"},"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/"}