{"paper_id":"2310.10500","title":"Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies","authors":["Kieran Wood","Samuel Kessler","Stephen J. Roberts","Stefan Zohren"],"paper_date":"2023-10-16","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2310.10500v2","page_url":"https://thequant.space/flowcharts/few-shot-learning-patterns-in-financial-time-series-for-tren/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Cross Attentive Time-Series Trend Network (X‑Trend), a few‑shot learning model that attends over a context set of financial regimes to make trend‑following forecasts.","quote":"We propose the Cross Attentive Time-Series Trend Network – X-Trend – which takes positions attending over a context set of financial time-series regimes.","summary":"Forecasting models for systematic trading strategies do not adapt quickly when financial market conditions rapidly change, as was seen in the advent of the COVID-19 pandemic in 2020, causing many forecasting models to take loss-making positions. To deal with such situations, we propose a novel…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are set to zero for each asset.","type":"execution","stated":"explicit","quote":"For this paper we set C(i) = 0 rather than assuming a cost for each asset, focusing…"},{"assumption":"Volatility targeting is used with a leverage factor σtgt/σ(i).","type":"model","stated":"explicit","quote":"We use volatility targeting [5, 26, 27], which introduces a leverage factor σtgt/σ(i)"},{"assumption":"An expanding window training approach is employed for out‑of‑sample testing.","type":"data","stated":"explicit","quote":"we use an expanding window approach, where we initially train on 1990 to 1995, test out‑of‑sample on the period from 1995 to 2000, expand the training window to from 1990 to 2000, then test out‑of‑sample on the subsequent 5 years and so on."},{"assumption":"Gaussian return distribution is assumed in low‑resource (zero‑shot) settings.","type":"statistical","stated":"explicit","quote":"the simpler assumption of Gaussian returns is favourable in a low‑resource setting."},{"assumption":"Change‑point detection is used to segment the context set into regimes.","type":"model","stated":"explicit","quote":"by segmenting the context set with CPD, we improve Sharpe by a further 11.3%, showing the benefit of constructing context sets with regimes."}]},"datasets":{"status":"available","items":[{"name":"Pinnacle Data Corp CLC Database futures contracts","provider":"Pinnacle Data Corp","kind":"market-prices","access":"commercial","period":"1990‑2023","universe":"50 most liquid continuous futures contracts","quote":"We backtest our X‑Trend variants on a portfolio of 50 of the most liquid, continuous futures contracts"}],"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":"For this paper we set C(i) = 0 rather than assuming a cost for each asset, focusing…","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"For this paper we set C(i) = 0 rather than assuming a cost for each asset, focusing…","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"X‑Trend improves Sharpe by 18.9% over the baseline (neural forecaster) and about 10‑fold over conventional time‑series momentum during 2018‑2023.","kind":"performance","quote":"During this 5‑year period X‑Trend improves upon the Sharpe of the baseline strategy by 16.9% and X‑Trend‑Q improves upon the baseline by 18.9%."},{"finding":"X‑Trend recovers from the COVID‑19 drawdown almost twice as quickly as a neural forecaster (162 vs 254 trading days).","kind":"performance","quote":"the drawdown ends after 162 trading days for X‑Trend‑Q compared to 254 days for the Baseline which is an entire year and almost twice as long as X‑Trend‑Q."},{"finding":"Zero‑shot X‑Trend achieves a Sharpe of 0.47 on unseen futures, outperforming loss‑making time‑series momentum baselines.","kind":"performance","quote":"we achieve a Sharpe of 0.47 compared to loss‑making time‑series momentum baselines, both deep‑learning based and conventional TSMOM."},{"finding":"Segmenting the context set with change‑point detection adds an 11.3% Sharpe improvement.","kind":"performance","quote":"by segmenting the context set with CPD, we improve Sharpe by a further 11.3%, showing the benefit of constructing context sets with regimes."},{"finding":"X‑Trend‑Q outperforms X‑Trend‑G by 7.1% in Sharpe in the few‑shot setting, indicating non‑Gaussian modeling benefits.","kind":"performance","quote":"Sharpe for X‑Trend‑Q outperforms X‑Trend‑G by 7.1% in the few‑shot setting over the turbulent period of 2018 to 2023."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":4,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":3},"independent_papers":[],"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/kieranjwood/x-trend","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":"2026-11-14T18:20:43Z"},"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/"}