{"paper_id":"2306.13661","title":"Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learning","authors":["Joel Ong","Dorien Herremans"],"paper_date":"2023-06-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.13661v1","page_url":"https://thequant.space/flowcharts/constructing-time-series-momentum-portfolios-with-deep-multi/","scores":{"empirical_rigor":8.5,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a multi-task learning time-series momentum model (MTL‑TSM) as a novel deep learning based portfolio optimization method.","quote":"We propose a multi-task learning time-series momentum model (MTL‑TSM), which is a novel portfolio optimization method based on deep multi‑task learning.","summary":"A diversified risk-adjusted time-series momentum (TSMOM) portfolio can deliver substantial abnormal returns and offer some degree of tail risk protection during extreme market events. The performance of existing TSMOM strategies, however, relies not only on the quality of the momentum signal but…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are set to 3 basis points per trade.","type":"execution","stated":"explicit","quote":"τ is the transaction cost (set as 3 basis points (bps))"},{"assumption":"All portfolios are volatility‑scaled to a target of 10% annualized volatility.","type":"model","stated":"explicit","quote":"During our backtest, we applied volatility scaling to all portfolios, bringing the volatility to a target of 10%."},{"assumption":"The Sharpe ratio is used as the loss function for training the neural network.","type":"statistical","stated":"explicit","quote":"Since our primary objective when developing the multi‑task model is to construct a portfolio with better risk‑adjusted performance, we employ the Sharpe ratio (Sharpe, 1994), as per Equation (6), as the loss function that is minimized during the training of our neural network model."},{"assumption":"Features are standardized using a 21‑day sliding‑window z‑score.","type":"model","stated":"explicit","quote":"Given that these features have varying scales, before using them as inputs to our model, we apply z‑score standardization with a sliding window of length 21 to our features."},{"assumption":"The backtest period is from January 2000 to December 2020 on continuous futures contracts.","type":"data","stated":"explicit","quote":"backtesting from January 2000 to December 2020 on a diversified portfolio of continuous futures contracts"}]},"datasets":{"status":"available","items":[{"name":"Continuous futures contracts portfolio","provider":null,"kind":"market-prices","access":"unknown","period":"2000-01 to 2020-12","universe":"diversified portfolio of continuous futures contracts","quote":"backtesting from January 2000 to December 2020 on a diversified portfolio of continuous futures contracts"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"Using the Bloomberg Terminal, we obtained the US MSCI Total Return Index data from January 2000 to December 2020.","mentions":1,"used_in":1},{"id":"quandl","name":"Nasdaq Data Link (Quandl)","provider":"Nasdaq","kind":"market-prices","access":"commercial","quote":"Instead, we evalu-ate our proposed model on the Stevens Continuous Futures data feed (Stevens Analytics, 2020) obtained through Nasdaq Data Link from January 1990 to December 2020.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Transaction cost set to 3 basis points per trade and incorporated into the return calculation.","quote":"τ is the transaction cost (set as 3 basis points (bps))","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction cost set to 3 basis points per trade and incorporated into the return calculation.","card_quote":"τ is the transaction cost (set as 3 basis points (bps))","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The MTL‑TSMOM strategy outperforms TSMOM and CTA‑MOM by 236 bps and 624 bps respectively over the 20‑year test period.","kind":"performance","quote":"In Table 2, the returns of our proposed strategy, which we refer to as MTL‑TSMOM, outperforms both TSMOM and CTA‑MOM by 236 bps and 624 bps, respectively, over the 20 year test period."},{"finding":"MTL‑TSMOM achieves an annualized return of 7.90% and Sharpe ratio of 0.81 after transaction costs.","kind":"performance","quote":"annualized return of 7.90% for the period of 1st January 2000 to 31st December 2020"},{"finding":"The strategy exhibits lower long‑term correlation to the US MSCI Total Return Index, making it a strong diversifier.","kind":"performance","quote":"our proposed model shows a low correlation to the US MSCI Total Return Index’s returns, thus presenting itself as an extremely attractive diversifier to existing stocks and bonds portfolios."},{"finding":"During the Global Financial Crisis and the 2020 Coronavirus Crash, the MTL‑TSMOM outperformed the US MSCI Total Return Index by 57% and 34.4% respectively.","kind":"performance","quote":"the US MSCI Total Return Index by 57% and 34.4% in the GFC and Coronavirus Crash of 2020, respectively."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":1,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2602.00776","title":"Explainable Patterns in Cryptocurrency Microstructure","paper_date":"2026-01-31","authors":["Bartosz Bieganowski","Robert Ślepaczuk"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/explainable-patterns-in-cryptocurrency-microstructure/"},"how":"extends","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/joelowj/mtl-tsmom","note":null},"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":"2026-11-14T18:26:03Z"},"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/"}