{"paper_id":"2308.11294","title":"Network Momentum across Asset Classes","authors":["Xingyue Pu","Stephen Roberts","Xiaowen Dong","Stefan Zohren"],"paper_date":"2023-08-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.11294v1","page_url":"https://thequant.space/flowcharts/network-momentum-across-asset-classes/","scores":{"empirical_rigor":6,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a graph learning model to infer dynamic networks among futures contracts and builds a network momentum trading strategy.","quote":"we propose a novel approach using a graph learning model [26] to infer dynamic networks among 64 continuous futures contracts across four asset classes","summary":"We investigate the concept of network momentum, a novel trading signal derived from momentum spillover across assets. Initially observed within the confines of pairwise economic and fundamental ties, such as the stock-bond connection of the same company and stocks linked through supply-demand…","strategy":"network momentum strategy"},"assumptions":{"status":"available","items":[{"assumption":"Graph signals are low‑frequency (low‑pass) components in the graph spectral domain.","type":"model","stated":"explicit","quote":"graph learning involves estimating a graph adjacency or Laplacian matrix with a model assumption that graph signals mainly consists of low frequency components in the graph spectral domain, i.e. low-pass graph signals"},{"assumption":"Each asset’s momentum features are linearly combined with edge weights to form network momentum covariates.","type":"model","stated":"explicit","quote":"For each asset, the covariates are network momentum features, which are weighted average of its connected assets’ individual momentum features, with edge values as weights"},{"assumption":"The linear regression model predicts a 1‑day volatility‑scaled return.","type":"model","stated":"explicit","quote":"The model aims to predict an asset’s future trend, targeted by its future 1‑day volatility‑scaled return"},{"assumption":"Turnover regularisation is not applied in the current strategy.","type":"execution","stated":"explicit","quote":"We reserve this for future research"},{"assumption":"All assets are treated as nodes in a symmetric, non‑negative adjacency matrix.","type":"model","stated":"explicit","quote":"The constraints guarantee the learned graph adjacency matrix is symmetric and non‑negative"}]},"datasets":{"status":"available","items":[{"name":"Daily prices of 64 continuous futures contracts","provider":"Pinnacle Data Crop CLC Database","kind":"market-prices","access":"commercial","period":"1990‑2022 (varying per asset)","universe":"Commodities, Equities, Fixed Income, Currencies futures","quote":"Our raw dataset contains the daily prices of 64 highly liquid ratio‑adjusted continuous futures contracts. These contracts are extracted from the Pinnacle Data Crop CLC Database2. The"}],"known":[],"sample":{"start":"2000","end":"2022","market":"futures","asset_class":"multi-asset","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":"Cost‑adjusted Sharpe is computed for pseudo‑costs c = {0, 0.5, 1, 2, 3, 4, 5} basis points.","card_quote":"c is the pseudo‑cost in basis points (bps). We consider c = {0, 0.5, 1, 2, 3, 4, 5} bps in Figure 3a","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The network momentum strategy achieves a Sharpe ratio of 1.5 and an annual return of 22% after volatility scaling (2000‑2022).","kind":"performance","quote":"By leveraging the learned networks, we construct a network momentum strategy that exhibits a Sharpe ratio of 1.5 and an annual return of 22%, after volatility scaling, from 2000 to 2022"},{"finding":"GMOM maintains a positive Sharpe up to 3 bps transaction cost and above 0.5 up to 2 bps, outperforming LinReg under costs.","kind":"performance","quote":"GMOM demonstrates resilience to transaction costs. It manages to maintain a positive Sharpe ratio up to a cost of 3bps, and a ratio above 0.5 up to 2bps"},{"finding":"Model‑based methods (LinReg, GMOM, RegCombo, SignCombo) exhibit higher turnover than model‑free methods (MACD, Long Only).","kind":"performance","quote":"model‑based methods, such as LinReg, GMOM, RegCombo, and SignCombo, exhibit higher turnovers, which is consistent with findings in the literature"},{"finding":"Combining individual momentum and network momentum features (RegCombo) improves portfolio performance relative to using either alone.","kind":"performance","quote":"a better portfolio can be generated when these two types of features are combined"}],"reported_performance":{"strategy":"network momentum strategy","sharpe":1.5,"sharpe_benchmark":null,"annual_return_pct":22,"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":16,"citations":{"cited_by_in_corpus":6,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":3,"unclassified":3},"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":"2026-11-14T18:23:13Z"},"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/"}