{"paper_id":"2601.04602","title":"Forecasting Equity Correlations with Hybrid Transformer Graph Neural Network","authors":["Jack Fanshawe","Rumi Masih","Alexander Cameron"],"paper_date":"2026-01-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.04602v1","page_url":"https://thequant.space/flowcharts/forecasting-equity-correlations-with-hybrid-transformer-grap/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a Temporal-Heterogeneous Graph Neural Network (THGNN) that combines a Transformer temporal encoder with a graph‑attention module to forecast 10‑day ahead stock‑stock correlations for S&P 500 constituents.","quote":"We cast 10-day ahead correlation prediction in Fisher-z space and train a Temporal-Heterogeneous Graph Neural Network (THGNN) to predict residual deviations from a rolling historical baseline.","summary":"This paper studies forward-looking stock-stock correlation forecasting for S&P 500 constituents and evaluates whether learned correlation forecasts can improve graph-based clustering used in basket trading strategies. We cast 10-day ahead correlation prediction in Fisher-z space and train a…","strategy":"THGNN forward‑looking SPONGEsym basket trading strategy"},"assumptions":{"status":"available","items":[{"assumption":"No slippage costs are considered in the backtest.","type":"execution","stated":"explicit","quote":"Firstly, no slippage costs are considered in the backtest so realized performance may be overstated."},{"assumption":"The model is trained only under one set of hyper‑parameters (e.g., Transformer sequence length, learning rate, attention heads).","type":"model","stated":"explicit","quote":"the THGNN has not been compared to alternative ML models (LSTM, CNN, alternative GNN‑based models), limiting comparative claims. Thirdly, the model has been trained only under one set of hyperparameters (such as Transformer sequence length, learning rate, attention heads), and therefore it is almost certain predictive "},{"assumption":"A stock is included in the daily graph only if it has at least 30 days of data within the preceding 33 trading days.","type":"data","stated":"explicit","quote":"Specifically, as the sequence length of the transformer is 30 days, if a stock has 30 days of data within 33 trading days it is included and if not, it is excluded from graph construction."},{"assumption":"Forward‑looking predicted correlation matrices replace backward‑looking rolling‑window correlations in the SPONGEsym clustering and trading engine.","type":"model","stated":"explicit","quote":"we retain their trading engine but use forward‑looking predicted correlation matrices from the THGNN, instead of backward‑looking rolling‑window correlations."}]},"datasets":{"status":"available","items":[{"name":"CRSP and Compustat data","provider":"WRDS","kind":"market-prices","access":"commercial","period":"2019-2024 (out‑of‑sample)","universe":"S&P 500 constituents","quote":"Equity data is obtained from CRSP and Computstat via WRDS, and macroeconomic variables from FRED.","known_id":"crsp"},{"name":"FRED macroeconomic variables","provider":"FRED","kind":"macro","access":"public","period":null,"universe":null,"quote":"Equity data is obtained from CRSP and Computstat via WRDS, and macroeconomic variables from FRED.","known_id":"fred"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"This is likely due to the fact that we use data from WRDS (CRSP) whereas, Korniejczuk and ´Slepaczuk (2024) use data from Yahoo Finance.","mentions":3,"used_in":3},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"This is likely due to the fact that we use data from WRDS (CRSP) whereas, Korniejczuk and ´Slepaczuk (2024) use data from Yahoo Finance.","mentions":4,"used_in":2},{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"This is likely due to the fact that we use data from WRDS (CRSP) whereas, Korniejczuk and ´Slepaczuk (2024) use data from Yahoo Finance.","mentions":2,"used_in":2},{"id":"fred","name":"FRED","provider":"Federal Reserve Bank of St. Louis","kind":"macro","access":"public","quote":"Equity data is obtained from CRSP and Computstat via WRDS, and macroeconomic variables from FRED.","mentions":2,"used_in":1}],"sample":{"start":"2019","end":"2024","market":"S&P 500 stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":null,"detail":"Flat fee of 0.05% per trade applied in robustness checks.","quote":"with a cost of 0.05% per trade from 2000-2024.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Flat fee of 0.05% per trade applied in robustness checks.","card_quote":"with a cost of 0.05% per trade from 2000-2024.","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The THGNN reduces MAE from 0.3071 (20‑day historical rolling window) to 0.2302 and RMSE from 0.3852 to 0.2940 over the 2019‑2024 out‑of‑sample period.","kind":"predictive-accuracy","quote":"The out‑of‑sample period (2019-2024) showed the model is able to reduce MAE from 0.3071 (20‑day historical rolling window) to 0.2302 and RMSE from 0.3852 to 0.2940."},{"finding":"Pearson and Spearman correlation between predicted and actual future correlations more than double to 0.778 and 0.795 respectively.","kind":"predictive-accuracy","quote":"The model also reduced bias and improves both Pearson and Spearman correlation more than double to 0.778 and 0.795 respectively."},{"finding":"Using forward‑looking correlations in SPONGEsym clustering yields an own strategy annualized return of 8.27% (Sharpe 0.86) without transaction costs, but performance drops to -0.46% (Sharpe 0.00) with a 0.05% cost.","kind":"performance","quote":"Own (No TC) 8.27 0.86; Own (0.05% TC) -0.46 0.00"},{"finding":"Attention diagnostics show the model consistently emphasizes macro‑financial drivers such as VIX, crude oil prices, the 10‑year U.S. Treasury yield, the trade‑weighted dollar, and sector identifiers.","kind":"other","quote":"Attention diagnostics show that the model consistently emphasizes a small set of macro‑financial drivers - most notably market volatility (VIX), crude oil prices, the 10‑year U.S. Treasury yield, the trade‑weighted dollar, and sector identifiers"}],"reported_performance":{"strategy":"THGNN forward‑looking SPONGEsym basket trading strategy","sharpe":1.837,"sharpe_benchmark":0.647,"annual_return_pct":19.2,"total_return_pct":null,"max_drawdown_pct":9.43},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":43,"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":"2026-11-14T17:16:50Z"},"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/"}