{"paper_id":"2308.12212","title":"Learning to Learn Financial Networks for Optimising Momentum Strategies","authors":["Xingyue Pu","Stefan Zohren","Stephen Roberts","Xiaowen Dong"],"paper_date":"2023-08-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.12212v1","page_url":"https://thequant.space/flowcharts/learning-to-learn-financial-networks-for-optimising-momentum/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes L2GMOM, an end-to-end machine learning framework that simultaneously learns financial networks and optimises trading signals for network momentum strategies.","quote":"To address these challenges, we propose L2GMOM, an end-to-end machine learning framework that simultaneously learns financial networks and optimises trading signals for network momentum strategies.","summary":"Network momentum provides a novel type of risk premium, which exploits the interconnections among assets in a financial network to predict future returns. However, the current process of constructing financial networks relies heavily on expensive databases and financial expertise, limiting…","strategy":"L2GMOM"},"assumptions":{"status":"available","items":[{"assumption":"Momentum spillover is subtly echoed in the historical pricing data.","type":"data","stated":"explicit","quote":"adopt the reasonable assumption that momentum spillover is subtly echoed in the historical pricing data, which are more readily accessible."},{"assumption":"An asset’s future performance can be influenced by the past performance of its linked assets.","type":"market","stated":"explicit","quote":"Network momentum strategy takes into account the interconnections of assets, assuming an asset’s future performance can be influenced by the past performance of its linked assets."},{"assumption":"Graph adjacency matrices have non‑negative edges.","type":"model","stated":"explicit","quote":"from Eq.(10b) contains only non-negative edges, as a result of enforcing the constraints of Eq.(9)."},{"assumption":"Volatility scaling targets a 15% annualised portfolio volatility.","type":"execution","stated":"explicit","quote":"we apply an additional layer of volatility scaling at the portfolio level to an annualised volatility target of 15% and report the above evaluation metrics."},{"assumption":"Turnover costs are measured in basis points per trade.","type":"execution","stated":"explicit","quote":"is the turnover cost in bps, varying from 0.5 to 5 bps."}]},"datasets":{"status":"available","items":[{"name":"64 ratio‑adjusted continuous future contracts","provider":"Pinnacle Data Crop CLC Database","kind":"market-prices","access":"commercial","period":"1990 to 2020","universe":"continuous futures contracts","quote":"Our dataset contains 64 ratio‑adjusted continuous future contracts obtained from the Pinnacle Data Crop CLC Database."}],"known":[],"sample":{"start":null,"end":null,"market":"future contracts","asset_class":"futures","frequency":null},"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":"Turnover cost c varies from 0.5 to 5 basis points and is subtracted from returns when computing cost‑adjusted Sharpe ratios.","card_quote":"is the turnover cost in bps, varying from 0.5 to 5 bps. As ex‑ante costs rise, all strategies see a drop in cost‑adjusted Sharpe ratios.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"L2GMOM achieves a Sharpe ratio of 1.74 over a 20‑year backtest on 64 futures contracts.","kind":"performance","quote":"Backtesting on 64 continuous future contracts demonstrates a significant improvement in portfolio profitability and risk control, with a Sharpe ratio of 1.74 across a 20-year period."},{"finding":"L2GMOM and L2GMOM_SR outperform benchmark strategies in both profitability and risk metrics.","kind":"performance","quote":"... L2GMOM also outperform‑ing GLinReg indicates that optimising the graph with respect to portfolio performance can yield higher returns."},{"finding":"L2GMOM_SR attains the lowest volatility, downside deviation, maximum drawdown and MDD duration among the tested models.","kind":"performance","quote":"L2GMOM_SR has the lowest volatility, downside deviation, MDD, and MDD duration in the raw signal, indicating that optimising with the Sharpe ratio can significantly reduce risk."},{"finding":"Graph‑learning strategies (GLinReg, L2GMOM, L2GMOM_SR) show better resilience to increasing turnover costs than non‑graph models.","kind":"performance","quote":"The proposed models, L2GMOM and L2GMOM_SR, also stay positive at 3 bps, showing resilience to increasing costs. Thus, graph learning strategies like GLinReg, L2GMOM, and L2GMOM_SR offer better cost resilience than LinReg."}],"reported_performance":{"strategy":"L2GMOM","sharpe":1.74,"sharpe_benchmark":null,"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":27,"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":"2026-11-14T18:23:00Z"},"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/"}