{"paper_id":"2309.00073","title":"Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction","authors":["Kelvin J. L. Koa","Yunshan Ma","Ritchie Ng","Tat-Seng Chua"],"paper_date":"2023-08-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.00073v2","page_url":"https://thequant.space/flowcharts/diffusion-variational-autoencoder-for-tackling-stochasticity/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Diffusion‑VAE (D‑Va) model, an end‑to‑end framework that combines a hierarchical VAE, a stochastic diffusion process and a denoising component for multi‑step stock price prediction.","quote":"We propose a solution that integrates a hierarchical VAE model, a stochastic diffusion process and a denoising component and implement it in an end-to-end model for stock prediction.","summary":"Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility, allowing financial institutions to price and hedge derivatives, and banks to quantify the risk in their trading books. Additionally, most financial regulators also require a liquidity horizon of…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Gaussian noise is added to input and target sequences via a diffusion process with a variance schedule.","type":"model","stated":"explicit","quote":"In the diffusion probabilistic model, we define a Markov chain of diffusion steps that slowly adds random Gaussian noise to the input sequence X to obtain the noisy samples X1, X2, · · · , X𝑁, where 𝑁 is the number of diffusion steps."},{"assumption":"Risk‑free interest rate is set to zero when computing Sharpe ratios.","type":"market","stated":"explicit","quote":"we set the risk-free interest rate to 0"},{"assumption":"Historical price data from Yahoo Finance is accurate and sufficient for training and evaluation.","type":"data","stated":"implied","quote":"The data is collected from Yahoo Finance3, and is processed in the same manner as the ACL18 dataset."}]},"datasets":{"status":"available","items":[{"name":"ACL18 StockNet dataset","provider":"ACL18","kind":"market-prices","access":"public","period":"01/01/2014 to 01/01/2017","universe":"88 high trade volume U.S. stocks across 9 major industries","quote":"It contains the historical prices of 88 high trade volume stocks from the U.S. market, which represents the top 8-10 stocks in capital size across 9 major industries. The duration of data ranges between 01/01/2014 to 01/01/2017."},{"name":"Extended StockNet dataset","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"01/01/2017 to 01/01/2023","universe":"110 top U.S. stocks from 11 major industries","quote":"We extend this dataset by collecting updated U.S. stock data from 01/01/2017 to 01/01/2023, taking the latest top 10 stocks from the 11 major industries","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The data is collected from Yahoo Finance3, and is processed in the same manner as the ACL18 dataset.","mentions":1,"used_in":1}],"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":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"D‑Va outperforms state‑of‑the‑art methods in multi‑step prediction accuracy and variance.","kind":"predictive-accuracy","quote":"Our Diffusion‑VAE (D‑Va) model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance."},{"finding":"Using D‑Va predictions with covariance regularization yields the highest Sharpe ratios across datasets and prediction horizons.","kind":"performance","quote":"using the predictions from D‑Va, together with covariance regularization, we are able to form portfolios that consistently achieve the best Sharpe ratios, even across difference sequence lengths 𝑇."},{"finding":"Regularization and D‑Va together achieve the best Sharpe ratio performance, surpassing an equal‑weight baseline despite using only historical price data.","kind":"performance","quote":"using D‑Va as the prediction model and applying regularization both help to improve the Sharpe ratio results, and combining both methods allow us to obtain the best Sharpe ratio performance."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":13,"by_independent_authors":9,"how_cited":{"used_as_baseline":1,"uses_method_or_data":2,"extends":0,"discusses_findings":0,"mentions":6,"unclassified":4},"independent_papers":[{"paper":{"paper_id":"2508.19609","title":"FinCast: A Foundation Model for Financial Time-Series Forecasting","paper_date":"2025-08-27","authors":["Zhuohang Zhu","Haodong Chen","Qiang Qu","Vera Chung"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/fincast-a-foundation-model-for-financial-time-series-foreca/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2402.07080","title":"RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search","paper_date":"2024-02-11","authors":["Tao Ren","Ruihan Zhou","Jinyang Jiang","Jiafeng Liang","Qinghao Wang","Yijie Peng"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/riskminer-discovering-formulaic-alphas-via-risk-seeking-mon/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2403.06779","title":"From Factor Models to Deep Learning: Machine Learning in Reshaping Empirical Asset Pricing","paper_date":"2024-03-11","authors":["Junyi Ye","Bhaskar Goswami","Jingyi Gu","Ajim Uddin","Guiling Wang"],"empirical_rigor":3,"page_url":"https://thequant.space/flowcharts/from-factor-models-to-deep-learning-machine-learning-in-res/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/koa-fin/dva","note":null},"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":"2026-11-14T18:23:12Z"},"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/"}