{"paper_id":"2402.06633","title":"MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction","authors":["Hao Qian","Hongting Zhou","Qian Zhao","Hao Chen","Hongxiang Yao","Jingwei Wang","Ziqi Liu","Fei Yu","Zhiqiang Zhang","Jun Zhou"],"paper_date":"2024-01-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2402.06633v1","page_url":"https://thequant.space/flowcharts/mdgnn-multi-relational-dynamic-graph-neural-network-for-com/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Multi‑relational Dynamic Graph Neural Network (MDGNN) framework for stock investment prediction.","quote":"propose a Multi-relational Dynamic Graph Neural Network (MDGNN)","summary":"The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such as economic indicators, financial reports, global news, and investor sentiment. Traditional…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Stock relationships are multifaceted and change on a daily basis.","type":"model","stated":"explicit","quote":"Given that the relationships between stocks are multifaceted and changing on a daily basis, we propose a Dynamic Graph Neural Network (DGNN) to capture and represent them."},{"assumption":"The closing price of a stock at each trading day is used as the target variable.","type":"data","stated":"explicit","quote":"For a stock node vit ∈Vt, the closing price at a trading day t is denoted as pit."},{"assumption":"Benchmark return is used to compute the ground‑truth label.","type":"data","stated":"explicit","quote":"yit = pi,t+1−pit pit −benchmarkt, in which benchmarkt is the return of the benchm…"}]},"datasets":{"status":"none_found","items":[],"known":[],"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":"MDGNN achieves the highest scores across all metrics on both CSI100 and CSI300 datasets, e.g., IC 0.0123, IR 0.0746, CR 0.2741, Prec@30 0.5081 on CSI100.","kind":"performance","quote":"MDGNN 0.0123 0.0746 0.2741 0.5081 0.0322 0.2488 0.9828 0.5232"},{"finding":"Ablation shows removing the meta‑path module causes the largest performance drop, confirming its importance.","kind":"performance","quote":"w/o meta-path 0.0216 0.1723 0.7502 0.5076"}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":6,"by_independent_authors":4,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":6},"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":"2026-11-14T18:16:03Z"},"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/"}