{"paper_id":"2407.15532","title":"Large-scale Time-Varying Portfolio Optimisation using Graph Attention Networks","authors":["Kamesh Korangi","Christophe Mues","Cristián Bravo"],"paper_date":"2024-07-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2407.15532v2","page_url":"https://thequant.space/flowcharts/large-scale-time-varying-portfolio-optimisation-using-graph/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel Graph Attention Network (GAT) based model for large‑scale mid‑cap portfolio optimisation.","quote":"We propose and empirically test a novel method that leverages Graph Attention networks (GATs), a subclass of Graph Neural Networks (GNNs).","summary":"Apart from assessing individual asset performance, investors in financial markets also need to consider how a set of firms performs collectively as a portfolio. Whereas traditional Markowitz-based mean-variance portfolios are widespread, network-based optimisation techniques offer a more flexible…","strategy":"GAT-based portfolio optimisation"},"assumptions":{"status":"available","items":[{"assumption":"No transaction costs are incurred when trading the equal‑weight benchmark.","type":"execution","stated":"explicit","quote":"For simplicity, however, we assume that there are no transaction costs1, and use this equal-weight portfolio as the market benchmark in our study."},{"assumption":"The classical mean‑variance model assumes normality of returns and absence of transaction costs.","type":"model","stated":"explicit","quote":"Assumptions about the normality of returns and absence of transaction costs"}]},"datasets":{"status":"available","items":[{"name":"30 years of mid‑cap firm data","provider":null,"kind":"market-prices","access":"unknown","period":"30 years","universe":"mid‑cap firms","quote":"This study utilises 30 years of data on mid-cap firms, creating graphs of firms using distance correlation and the Triangulated Maximally Filtered Graph approach."}],"known":[],"sample":{"start":null,"end":null,"market":"mid-cap equities","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"For simplicity, however, we assume that there are no transaction costs1, and use this equal-weight portfolio as the market benchmark in our study.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"For simplicity, however, we assume that there are no transaction costs1, and use this equal-weight portfolio as the market benchmark in our study.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The GAT model achieves the highest Sharpe ratio (1.082) on test data, outperforming all benchmark strategies.","kind":"performance","quote":"On the test data, the GAT models have the highest Sharpe ratio of 1.082."},{"finding":"The GAT portfolio exhibits the lowest excess turnover (4.10%) compared with mean‑variance (5.50%) and network index (4.84%) models.","kind":"performance","quote":"With an overall excess turnover of 4.10%, the GAT model is thus associated with a relative reduction of 25% and 15%, compared to the mean-variance and network index models, respectively."},{"finding":"The GAT model holds far fewer firms than the mean‑variance implementation, reflecting a regularisation mechanism.","kind":"performance","quote":"the GAT model requires holding far fewer firms than our mean-variance implementation, which is unsurprising given that the former includes a regularisation mechanism that is lacking in the latter."}],"reported_performance":{"strategy":"GAT-based portfolio optimisation","sharpe":1.082,"sharpe_benchmark":0.83,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":29,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"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":"2026-11-14T18:05:34Z"},"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/"}