{"paper_id":"2511.12129","title":"A Practical Machine Learning Approach for Dynamic Stock Recommendation","authors":["Hongyang Yang","Xiao-Yang Liu","Qingwei Wu"],"paper_date":"2025-11-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.12129v1","page_url":"https://thequant.space/flowcharts/a-practical-machine-learning-approach-for-dynamic-stock-reco/","scores":{"empirical_rigor":8,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a practical scheme that dynamically recommends and buys the top 20% of S&P 500 stocks each quarter using five machine‑learning models and selects the best‑performing model each period.","quote":"In this paper, we propose a practical scheme that recommends stocks from S&P 500 using machine learning. Our basic idea is to buy and hold the top 20% stocks dynamically.","summary":"Stock recommendation is vital to investment companies and investors. However, no single stock selection strategy will always win while analysts may not have enough time to check all S&P 500 stocks (the Standard & Poor’s 500). In this paper, we propose a practical scheme that recommends stocks from…","strategy":"Dynamic top‑20% quarterly stock selection with min‑variance allocation"},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are assumed to be 0.1% (1/1000) of the trade value.","type":"execution","stated":"explicit","quote":"we consider our transaction cost to be 1/1000 of the value of that trade."},{"assumption":"The strategy is long‑only with no leverage and a maximum position size of 5% of portfolio value.","type":"model","stated":"explicit","quote":"... limits on position sizes (maximum of position size is 5% of portfolio value)"},{"assumption":"Rolling windows of 4–10 years are used for training and a one‑year window for testing.","type":"data","stated":"explicit","quote":"Rolling windows for training ranges from 16-quarter (4-year) to a maximum of 40-quarter (10-year). This training rolling window is followed by an one-year window for testing"},{"assumption":"Outlier records with release dates after the trade date (≈0.84% of data) are removed.","type":"data","stated":"explicit","quote":"we delete outlier records that indicate a release date (rdq) after the trade date, which include about 0.84% of the dataset."},{"assumption":"Missing factor data >5% leads to factor deletion; stocks with the most missing data are removed.","type":"data","stated":"explicit","quote":"if one factor has more than 5% missing data, we delete this factor; if a certain stock generates the most missing data, we delete this stock."},{"assumption":"Quarterly trade dates are lagged by two months to accommodate non‑standard quarter ends.","type":"execution","stated":"explicit","quote":"We also extend the trade date by two months lag beyond the standard quarter end date in case some companies have a non-standard quarter end date"}]},"datasets":{"status":"available","items":[{"name":"Compustat database","provider":"Wharton Research Data Services (WRDS)","kind":"fundamentals","access":"commercial","period":"06/01/1990 to 06/01/2017","universe":"S&P 500 component stocks (about 1142 stocks)","quote":"... period of 27 years (from 06/01/1990 to 06/01/2017). We use all historical S&P 500 component stocks (about 1142 stocks) as the S&P 500 pool","known_id":"compustat"}],"known":[{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"B. Data Preprocessing The data for this project is mainly taken from Compustat database accessed through Wharton Research Data Services (WRDS) [9].","mentions":3,"used_in":2},{"id":"compustat","name":"Compustat","provider":"S&P Global","kind":"fundamentals","access":"commercial","quote":"B. Data Preprocessing The data for this project is mainly taken from Compustat database accessed through Wharton Research Data Services (WRDS) [9].","mentions":1,"used_in":1}],"sample":{"start":"1995","end":"2007","market":"S&P 500 stocks","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Costs are modeled as 0.1% of trade value (1/1000 of the trade value).","quote":"we consider our transaction cost to be 1/1000 of the value of that trade.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Costs are modeled as 0.1% of trade value (1/1000 of the trade value).","card_quote":"we consider our transaction cost to be 1/1000 of the value of that trade.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"All three portfolio allocation methods (equally weighted, mean‑variance, min‑variance) outperformed the market in cumulative return and annualized return.","kind":"performance","quote":"all three portfolio allocation methods outperform the market"},{"finding":"The min‑variance portfolio delivered the highest overall end value (12.81 million) compared to equally weighted (22.14 million) and the S&P 500 (1.93 million) when starting with 1 million.","kind":"performance","quote":"End Value in million 10.9917 22.1383 12.81498 1.933153"},{"finding":"The strategy’s annualized returns were 8.29% (Mean‑Var), 10.77% (Equally), and 9.87% (Min‑Var) versus 5.22% for the S&P 500.","kind":"performance","quote":"Annualized Return 8.29% 10.77% 9.87% 5.22%"},{"finding":"The proposed machine‑learning scheme consistently outperformed the long‑only S&P 500 benchmark in Sharpe ratio and cumulative returns.","kind":"performance","quote":"Our empirical results show that the proposed scheme outperforms the long-only strategy on the S&P 500 index in terms of Sharpe ratio and cumulative returns."}],"reported_performance":{"strategy":"Dynamic top‑20% quarterly stock selection with min‑variance allocation","sharpe":0.462,"sharpe_benchmark":null,"annual_return_pct":9.87,"total_return_pct":1181.5,"max_drawdown_pct":46.3},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":30,"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":true,"code_url":"https://github.com/AI4Finance-Foundation/Dynamic-Stock-Recommendation-Machine_Learning-Published-Paper-IEEE","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":"2026-11-14T17:21:47Z"},"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/"}