{"paper_id":"2403.14063","title":"DiffSTOCK: Probabilistic relational Stock Market Predictions using Diffusion Models","authors":["Divyanshu Daiya","Monika Yadav","Harshit Singh Rao"],"paper_date":"2024-03-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2403.14063v1","page_url":"https://thequant.space/flowcharts/diffstock-probabilistic-relational-stock-market-predictions/","scores":{"empirical_rigor":4,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a novel framework that combines denoising diffusion probabilistic models with relational market data, and introduces a deterministic architecture called MaTCHS using Masked Relational Transformers.","quote":"To surmount these challenges, we propose a novel framework that synergizes DDPMs with relational market data, encapsulating the spatio-temporal strengths of deterministic models and the uncertainty handling of DDPMs.","summary":"In this work, we propose an approach to generalize denoising diffusion probabilistic models for stock market predictions and portfolio management. Present works have demonstrated the efficacy of modeling interstock relations for market time-series forecasting and utilized Graph-based learning…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Stock data has a low signal‑to‑noise ratio which hampers deterministic models.","type":"data","stated":"explicit","quote":"Yet, a challenge persists in the realm of stock prediction: the low signal-to-noise ratio inherent in stock data."},{"assumption":"Trading performance is evaluated using a daily buy‑hold‑sell strategy without accounting for transaction costs.","type":"execution","stated":"explicit","quote":"For portfolio management using predicted prices we will adopt a daily buy‑hold‑sell strategy as described by [5]."}]},"datasets":{"status":"available","items":[{"name":"NASDAQ","provider":null,"kind":"market-prices","access":"public","period":null,"universe":null,"quote":"We test on NASDAQ [6], NYSE [6] and StockNet [23]."},{"name":"NYSE","provider":null,"kind":"market-prices","access":"public","period":null,"universe":null,"quote":"We test on NASDAQ [6], NYSE [6] and StockNet [23]."},{"name":"StockNet","provider":null,"kind":"market-prices","access":"public","period":null,"universe":null,"quote":"We test on NASDAQ [6], NYSE [6] and StockNet [23]."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"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":"Diffusion‑based MaTCHS achieves the highest performance on StockNet, with F1 0.631 ± 2e‑3, accuracy 0.634 ± 2e‑3, MCC 0.225 ± 6e‑3 and CRPS 0.049, outperforming prior diffusion models.","kind":"performance","quote":"MaTCHS with Diffusion (ours) 0.631 ± 2e −3 0.634 ± 2e −3 0.225 ± 6e −3 0.049"},{"finding":"MaTCHS with Diffusion improves Sharpe ratios by 7.92% and 6.18% compared to the STHAN‑SR baseline on NASDAQ and NYSE datasets.","kind":"performance","quote":"Sharpe ratios of 7.92% and 6.18% suggesting consi…"},{"finding":"The diffusion‑based version of MaTCHS outperforms all other models in F1, accuracy, and MCC on the StockNet dataset.","kind":"predictive-accuracy","quote":"The Diffusion‑based MaTCHS excels on the StockNet Dataset[23], outperforming all other models in F1, accuracy, and MCC metrics"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"citations":{"cited_by_in_corpus":4,"by_independent_authors":4,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":3,"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":"2026-11-14T18:12:39Z"},"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/"}