{"paper_id":"2401.06139","title":"Stockformer: A Price-Volume Factor Stock Selection Model Based on Wavelet Transform and Multi-Task Self-Attention Networks","authors":["Bohan Ma","Yushan Xue","Yuan Lu","Jing Chen"],"paper_date":"2023-11-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.06139v2","page_url":"https://thequant.space/flowcharts/stockformer-a-price-volume-factor-stock-selection-model-bas/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Stockformer, a price‑volume factor stock selection model that combines wavelet transformation with a multitask self‑attention network.","quote":"this paper introduces Stockformer, a price-volume factor stock selection model that integrates wavelet transformation and a multitask self-attention network","summary":"As the Chinese stock market continues to evolve and its market structure grows increasingly complex, traditional quantitative trading methods are facing escalating challenges. Particularly, due to policy uncertainty and the frequent market fluctuations triggered by sudden economic events, existing…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The model assumes industry and market value neutralization removes industry and size effects.","type":"model","stated":"implied","quote":"Industry and market value neutralization are employed to eliminate the influence of a stock’s industry and market value."},{"assumption":"The backtesting assumes a transaction cost of 0.1% per side (with stamp duty changes).","type":"execution","stated":"implied","quote":"The transaction cost is 0.1% per side, with stamp duty at 0.1% before August 27, 2023, and 0.05% thereafter."},{"assumption":"The data split uses a rolling window of two‑year training, three‑month validation, and three‑month test periods.","type":"data","stated":"implied","quote":"the data is divided into two years of trading data as the training set (486 days), followed by three months of trading data for the validation set (81 days), and another three months for the test set (81 days)"},{"assumption":"Only stocks that are not delisted, have positive net assets, are not newly issued, and are not under risk warning are included.","type":"data","stated":"implied","quote":"Stocks that were delisted, had negative net assets, were newly issued, or were under risk warning were excluded."},{"assumption":"The TopK‑Dropout strategy assumes that selecting the top‑k ranked stocks yields better performance.","type":"model","stated":"implied","quote":"The core idea of the Topk-Dropout strategy is to select stocks that rank high in factor values, assuming these stocks are more likely to perform well in the future."}]},"datasets":{"status":"available","items":[{"name":"CSI 300 index constituents","provider":"CSI","kind":"market-prices","access":"public","period":"2018-03-01 to 2024-01-30","universe":"CSI 300 index","quote":"We utilize stock market data from March 1, 2018, to January 30, 2024, for analysis."}],"known":[{"id":"qlib","name":"Qlib datasets","provider":"Microsoft","kind":"market-prices","access":"public","quote":"Utilizing the Alpha360 factor library developed by Microsoft’s Qlib framework, we constructed 360 price-volume factors, categorized into six types, with each type comprising 60 factors.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"polarity","card_detail":"0.1% per side, with stamp duty 0.1% before 2023‑08‑27 and 0.05% thereafter","card_quote":"The transaction cost is 0.1% per side, with stamp duty at 0.1% before August 27, 2023, and 0.05% thereafter.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Stockformer achieves a directional accuracy of 57.46%, higher than all baselines.","kind":"predictive-accuracy","quote":"Notably, it achieves a directional accuracy of 57.46%, significantly higher than other models."},{"finding":"In backtesting, Stockformer yields annualized returns of 239.73% (rising market), -15.18% (falling market), and 44.48% (volatile market).","kind":"performance","quote":"Backtesting results indicate that the Stockformer-based stock selection model achieves annualized returns of 239.73%, -15.18%, and 44.48% in rising, falling, and fluctuating markets, respectively"},{"finding":"Maximum drawdowns are 3.07% (rising), 19.6% (falling), and 4.14% (volatile) with Sharpe ratios of 8.46, -0.56, and 2.71 respectively.","kind":"performance","quote":"with maximum drawdowns of 3.07%, 19.6%, and 4.14%; and Sharpe ratios of 8.46, -0.56, and 2.71."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":37,"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":1,"unclassified":2},"independent_papers":[],"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/Eric991005/Multitask-Stockformer","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":"2026-11-14T18:19:02Z"},"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/"}