{"paper_id":"2408.01499","title":"NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equities","authors":["Achintya Gopal"],"paper_date":"2024-08-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2408.01499v1","page_url":"https://thequant.space/flowcharts/neuralfactors-a-novel-factor-learning-approach-to-generativ/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes NeuralFactors, a novel machine‑learning based factor analysis model that outputs factor exposures and returns using a VAE‑style training.","quote":"we introduce NeuralFactors, a novel machine-learning based approach to factor analysis where a neural network outputs factor exposures and factor returns, trained using the same methodology as variational autoencoders.","summary":"The use of machine learning for statistical modeling (and thus, generative modeling) has grown in popularity with the proliferation of time series models, text-to-image models, and especially large language models. Fundamentally, the goal of classical factor modeling is statistical modeling of…","strategy":"NeuralFactors"},"assumptions":{"status":"available","items":[{"assumption":"The universe consists of the point‑in‑time constituents of the S&P 500.","type":"data","stated":"explicit","quote":"we use the point-in-time constituents of the S&P 500 as our universe"},{"assumption":"Daily price data are used for training, validation and testing.","type":"data","stated":"explicit","quote":"We use daily data and split it into three pieces: the training set which contains data from the beginning of 1996 to the end of 2013, the validation set which contains data from the beginning of 2014 to the end of 2018, and the test set which contains data from the beginning of 2019 to the end of 2023."},{"assumption":"The number of neural‑network forward passes is independent of the number of samples required.","type":"model","stated":"explicit","quote":"in NeuralFactors, the number of neural network forward passes is independent of the number of samples required."}]},"datasets":{"status":"available","items":[{"name":"Point‑in‑time constituents of the S&P 500","provider":"Bloomberg","kind":"market-prices","access":"commercial","period":"1996‑2023","universe":"S&P 500 constituents","quote":"training set which contains data from the beginning of 1996 to the end of 2013","known_id":"bloomberg"}],"known":[],"sample":{"start":null,"end":null,"market":"equity returns","asset_class":"equities","frequency":null},"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":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"NeuralFactors outperforms BDG and PPCA in negative log‑likelihood.","kind":"performance","quote":"we are able to outperform BDG and PPCA in terms of negative log-likelihood (Section 5.2.1)"},{"finding":"NeuralFactors outperforms BDG and PPCA in covariance forecasting and portfolio optimization.","kind":"performance","quote":"NeuralFactors, when applied to equity returns, outperforms probabilistic PCA (PPCA) and BDG"},{"finding":"For VaR analysis NeuralFactors beats PPCA and BDG, but GARCH still has lower calibration error.","kind":"performance","quote":"while it outperforms PPCA and BDG on the test set, GARCH still outperforms NeuralFactors in terms of calibration error"},{"finding":"Attention‑based architecture significantly outperforms LSTM models.","kind":"performance","quote":"We found attention significantly outperforms LSTMs"},{"finding":"Increasing training data length improves performance, contradicting the belief that non‑stationarity requires shorter windows.","kind":"statistical","quote":"the performance improved monotonically with more training data. In other words, the belief that non-stationarity requires us to use fewer years of training data appears to be incorrect and that more data consistently improves performance."}],"reported_performance":{"strategy":"NeuralFactors","sharpe":1.87,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2406.08041","title":"HARd to Beat: The Overlooked Impact of Rolling Windows in the Era of Machine Learning","paper_date":"2024-06-12","authors":["Francesco Audrino","Jonathan Chassot"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/hard-to-beat-the-overlooked-impact-of-rolling-windows-in-th/"},"question":"Does a larger training window length improve model performance (lower RMSE)?","this_paper_finding":"Increasing training data length improves performance, contradicting the belief that non‑stationarity requires shorter windows.","other_paper_finding":"Larger training windows generally lead to lower RMSE for the HAR model.","other_paper_quote":"larger training windows generally lead to lower prediction errors.","note":"Both findings report that increasing the training window length leads to better performance—A observes lower RMSE with larger windows, and B finds longer data improves results, so B supports A.","confidence":0.798},{"paper":{"paper_id":"2502.15813","title":"Stock Price Prediction Using a Hybrid LSTM-GNN Model: Integrating Time-Series and Graph-Based Analysis","paper_date":"2025-02-19","authors":["Meet Satishbhai Sonani","Atta Badii","Armin Moin"],"empirical_rigor":7,"page_url":"https://thequant.space/flowcharts/stock-price-prediction-using-a-hybrid-lstm-gnn-model-integr/"},"question":"Does using longer training windows improve equity price prediction performance and generalisation?","this_paper_finding":"Increasing training data length improves performance, contradicting the belief that non‑stationarity requires shorter windows.","other_paper_finding":"Expanding window training improved adaptability, mitigated concept drift, and enhanced generalisation.","other_paper_quote":"The expanding window training approach offers several key advantages. Firstly, it enhances adaptability","note":"Both findings report that expanding the training window boosts performance, mitigates concept drift and enhances generalisation, contrary to the belief that short windows are needed.","confidence":0.769}],"contradicts":[],"qualifies":[],"compared_with":33,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"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":"2026-11-14T18:04:58Z"},"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/"}