{"paper_id":"2508.18592","title":"Combined machine learning for stock selection strategy based on dynamic weighting methods","authors":["Lin Cai","Zhiyang He","Caiya Zhang"],"paper_date":"2025-08-26","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.18592v1","page_url":"https://thequant.space/flowcharts/combined-machine-learning-for-stock-selection-strategy-based/","scores":{"empirical_rigor":6,"math_complexity":5.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel stock selection strategy framework that combines multiple machine learning algorithms with dynamic weighting methods.","quote":"This paper proposes a novel stock selection strategy framework based on combined machine learning algorithms.","summary":"This paper proposes a novel stock selection strategy framework based on combined machine learning algorithms. Two types of weighting methods for three representative machine learning algorithms are developed to predict the returns of the stock selection strategy. One is static weighting based on…","strategy":"ICMean weighted combined forecast"},"assumptions":{"status":"available","items":[{"assumption":"Training data for each prediction cycle consists of the previous 12 months of historical data.","type":"data","stated":"implied","quote":"During each prediction cycle, the training set is constructed using historical data from the previous 12-month period."},{"assumption":"Realized returns are adjusted for a flat transaction cost of 0.3%.","type":"execution","stated":"implied","quote":"Realized returns are adjusted to account for transaction costs, with the total cost rate set at 0.3%."},{"assumption":"Information Coefficient (IC) values are computed via Spearman correlation between predicted and actual returns.","type":"model","stated":"implied","quote":"we calculate the IC values through Spearman correlation between predicted returns and real returns, which can reflect both the direction and m…"}]},"datasets":{"status":"available","items":[{"name":"CSI 300 index data","provider":null,"kind":"market-prices","access":"public","period":null,"universe":"CSI 300 constituents","quote":"Using CSI 300 index data, we empirically evaluate the strategy' s backtested performance and model predictive accuracy."},{"name":"Publicly accessible databases","provider":null,"kind":"other","access":"public","period":null,"universe":null,"quote":"The data employed in this study are obtained from publicly accessible databases[11][12]."}],"known":[],"sample":{"start":"2020-01","end":"2022-12","market":"CSI 300 Index","asset_class":"equities","frequency":"monthly"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"partial","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"A flat total cost rate of 0.3% is applied to realized returns.","card_quote":"Realized returns are adjusted to account for transaction costs, with the total cost rate set at 0.3%.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"IC‑based weighting (especially ICMean) yields the highest backtested returns, far exceeding evaluation‑metric weighting and single‑model approaches.","kind":"performance","quote":"the strategy returns based on IC Mean and IC IR stand at 39.09% and 29.89%, respectively."},{"finding":"Combined machine learning algorithms significantly outperform single‑model approaches in backtested returns.","kind":"performance","quote":"The strategy by combined machine learning algorithms significantly outperforms single-model approaches in backtested returns."}],"reported_performance":{"strategy":"ICMean weighted combined forecast","sharpe":33.06,"sharpe_benchmark":0,"annual_return_pct":39.09,"total_return_pct":null,"max_drawdown_pct":10.92},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":12,"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":"2026-11-14T17:28:49Z"},"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/"}