{"paper_id":"2609.25617","title":"Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting","authors":["Hengyi Yang","Sida Lin","Yiyan Qi","Yankai Chen","Haohan Zhang","Xianhua Peng","Jian Guo"],"paper_date":"2026-09-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2609.25617v1","page_url":"https://thequant.space/flowcharts/hierarchical-multi-task-learning-with-liquidity-aware-signals-for-stock/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes LiMT, a hierarchical multi‑task learning framework that integrates liquidity‑aware signals for stock price forecasting.","quote":"we propose LiMT, a Hierarchical Multi-Task Learning framework that integrates liquidity-aware signals for stock price forecasting.","summary":"Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns. While recent deep-learning models have raised forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate…","strategy":"LiMT with Adaptive Portfolio Optimization (APO)"},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are 10 basis points per trade and each stock’s traded value is capped at 2% of its daily turnover.","type":"execution","stated":"explicit","quote":"per trade, and cap the traded value of each stock at 2% of its daily turnover."},{"assumption":"A participation‑rate cap of 2% is imposed on portfolio turnover.","type":"execution","stated":"explicit","quote":"α = 2% is the participation-rate cap, Ai,t is realized turnover, and C is the portfolio capital."},{"assumption":"Data are split into training (2008‑01‑01 to 2014‑12‑31), validation (2015‑01‑01 to 2016‑12‑31) and test (2017‑01‑01 to 2020‑08‑01).","type":"data","stated":"explicit","quote":"training/validation/test splits of 2008-01-01 to 2014-12-31, 2015-01-01 to 2016-12-31, and 2017-01-01 to 2020-08-01."}]},"datasets":{"status":"available","items":[{"name":"CSI300","provider":null,"kind":"benchmark","access":"public","period":"2008-2020","universe":"largest and most liquid Chinese A‑share stocks","quote":"We evaluate LiMT on the Chinese A-share market using CSI300 and CSI500 constituents. CSI300 covers the largest and most liquid stocks, while CSI500 extends evaluation to a broader mid-cap universe. The data span 2008–2020"},{"name":"CSI500","provider":null,"kind":"benchmark","access":"public","period":"2008-2020","universe":"broader mid‑cap Chinese A‑share stocks","quote":"We evaluate LiMT on the Chinese A-share market using CSI300 and CSI500 constituents. CSI300 covers the largest and most liquid stocks, while CSI500 extends evaluation to a broader mid-cap universe. The data span 2008–2020"}],"known":[{"id":"qlib","name":"Qlib datasets","provider":"Microsoft","kind":"market-prices","access":"public","quote":"We use the public Alpha158 feature set from Qlib [28], with lookback window τ = 21 and prediction horizon w = 1 day.","mentions":4,"used_in":1}],"sample":{"start":"2017","end":"2020","market":"CSI300 Chinese A‑share stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"10 basis points per trade, with each stock’s traded value capped at 2% of its daily turnover.","quote":"per trade, and cap the traded value of each stock at 2% of its daily turnover.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"10 basis points per trade, with each stock’s traded value capped at 2% of its daily turnover.","card_quote":"per trade, and cap the traded value of each stock at 2% of its daily turnover.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"APO improves annualized return from 3.99% to 10.01% and Sharpe ratio from 1.22 to 1.86 compared with equal‑weighting.","kind":"performance","quote":"Relative to equal weighting, annualized return rises from 3.99% to 10.01%, OSR from 32.13% to 38.00%, and Sharpe ratio from 1.22 to 1.86"},{"finding":"LiMT ranks first on all four metrics across both CSI300 and CSI500, achieving 56.22% and 51.98% gains in excess return and information ratio on CSI300 over the strongest baseline.","kind":"performance","quote":"LiMT ranks first on all four metrics across both datasets. The gains are especially pronounced on the portfolio-oriented metrics: on CSI300, excess annualized return and excess information ratio improve by 56.22% and 51.98% over the strongest baseline"}],"reported_performance":{"strategy":"LiMT with Adaptive Portfolio Optimization (APO)","sharpe":1.86,"sharpe_benchmark":1.22,"annual_return_pct":10.01,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":37,"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":"2026-11-14T17:04:41Z"},"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/"}