{"paper_id":"2611.19937","title":"AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data","authors":["Annan Wang","Yuchen Xie","Yu Cen","Leon Liangyu Chen","Qianyu Julie Zhu","Xin Li","Tianyi Wei","Weisi Lin"],"paper_date":"2026-11-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2611.19937","page_url":"https://thequant.space/flowcharts/allocflow-end-to-end-portfolio-trading-action-generation-from-raw-market-data/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes AllocFlow, an end‑to‑end cross‑asset flow‑matching Transformer that generates joint continuous signed portfolio allocations directly from raw multi‑asset market histories.","quote":"We present AllocFlow, an end-to-end flow-matching framework that directly generates joint portfolio allocations from raw multi-asset market histories.","summary":"Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportunities. However, traditional pipelines often…","strategy":"AllocFlow"},"assumptions":{"status":"available","items":[{"assumption":"Trading is performed on hourly cryptocurrency perpetual futures with a flat 5 bps fee per unit of absolute traded weight.","type":"execution","stated":"explicit","quote":"Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. This fee is the maximum of the base-tier taker fees of major perpetual-futures venues and the fees in prior crypto trading papers, and the median half-spread of the traded contracts is only 0.24 bps (Appendix C.3).","support":"full"},{"assumption":"The eligible asset universe is reconstituted weekly as the 20 assets with highest cumulative trading volume over the prior 60 days.","type":"market","stated":"explicit","quote":"Every week, the eligible list is recomputed as the 20 assets with the highest cumulative trading volume in the preceding 60 days. This causal reconstitution tests a changing opportunity set rather than a list selected with knowledge of the full test period.","support":"full"},{"assumption":"The Kronos encoder is frozen after pre‑training that ends in June 2024 and contains no information from the test period.","type":"model","stated":"explicit","quote":"Kronos pretraining ends in June 2024 [46], before the hourly test from November 2, 2024, to December 31, 2025; thus the frozen encoder has no test-period information in its weights.","support":"full"},{"assumption":"Orders are executed at the target weight change each hour without additional market impact beyond the stated fee.","type":"execution","stated":"implied","quote":"Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. Our backtest therefore uses the most conservative setting: it charges the base-tier taker fee on every change of the target book at every hourly rebalance, although a policy that trades toward a target book can execute with limit","support":"full"},{"assumption":"All price and volume data are publicly available and free to use.","type":"data","stated":"explicit","quote":"Evaluation design We use cryptocurrency perpetual futures (futures contracts without expiry that can be held long or short) because granular historical trading records are freely and publicly available over long periods.","support":"full"},{"assumption":"Flow matching provides a suitable stochastic policy class for joint allocation of signed weights.","type":"model","stated":"explicit","quote":"Flow matching suits portfolio allocation for three reasons. First, the action is a joint distribution over complete books of signed weights, for example, when several correlated assets are candidates for the same short.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Cryptocurrency perpetual futures (hourly bars)","provider":"public exchanges (e.g., Binance, OKX, Hyperliquid)","kind":"market-prices","access":"public","period":null,"universe":"weekly top‑20 assets by 60‑day volume","quote":"Evaluation design We use cryptocurrency perpetual futures (futures contracts without expiry that can be held long or short) because granular historical trading records are freely and publicly available over long periods. Policy training and test samples are strictly separated in time.","support":"full","known_id":"binance"}],"known":[],"sample":{"start":"2020-01","end":"2025-12","market":"cryptocurrency perpetual futures","asset_class":"crypto","frequency":"intraday"},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"A flat 5 bps fee per unit of absolute traded weight is applied to every change of the target book; median half‑spread is 0.24 bps.","quote":"Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. This fee is the maximum of the base-tier taker fees of major perpetual-futures venues and the fees in prior crypto trading papers, and the median half-spread of the traded contracts is only 0.24 bps (Appendix C.3).","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat 5 bps fee per unit of absolute traded weight is applied to every change of the target book; median half‑spread is 0.24 bps.","card_quote":"Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. This fee is the maximum of the base-tier taker fees of major perpetual-futures venues and the fees in prior crypto trading papers, and the median half-spread of the traded contracts is only 0.24 bps (Appendix C.3).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Group‑relative RL refinement raises the annualized net return of the imitation policy from 27.79 % to 51.38 % and its Calmar ratio from 0.955 to 4.043, surpassing the teacher strategy on every metric.","kind":"performance","quote":"On hourly cryptocurrency perpetual futures, RL refinement raises the annualized net return of the imitation policy from $27.79\\%$ to $51.38\\%$ and its Calmar ratio from $0.955$ to $4.043$, surpassing the teacher strategy on every metric, and AllocFlow reaches a Calmar ratio of $4.90$ on six further months of unseen 2026 data without retraining.","support":"full"},{"finding":"On six months of unseen 2026 data, AllocFlow achieves a Calmar ratio of 4.90 without retraining.","kind":"performance","quote":"Out-of-sample period Return ↑ MDD ↓ Sharpe ↑ Calmar ↑ Nov 2024–Dec 2025 (Table 1) 51.38 ±2.04 12.81 ±1.51 2.192 ±0.086 4.043 ±0.379 Jan–Jun 2026 (new) 62.53 12.77 2.06 4.90 C.3.","support":"full"},{"finding":"A parameter‑matched Gaussian policy trained with the same objective attains at most a Calmar of 1.92, less than half of the flow policy’s 4.043.","kind":"performance","quote":"Across exploration scales σ (Table 2b), it reaches a Calmar of at most 1.92, versus 4.043 for the flow policy, and stays below 1 in the other four settings.","support":"full"},{"finding":"Replacing the frozen Kronos encoder with a frozen iTransformer causes severe performance loss (negative returns and Calmar), showing the importance of good market features.","kind":"performance","quote":"Replacing frozen Kronos with a frozen iTransformer while keeping the flow head loses heavily after both IL and RL on the same ledger (Table 5), and reward refinement does not recover the Kronos-conditioned performance. With the losing Kronos-direct deployment, this shows that good market features become valuable only when a suitable head learns to allocate from them.","support":"full"},{"finding":"Reward ablation shows that training with a Sharpe‑based reward yields the highest Calmar (4.043) while other reward choices either reduce Calmar or produce negative returns.","kind":"performance","quote":"Cumulative return gives the highest annualized return, but the Sharpe-trained policy has the smallest MDD and highest Calmar while trading more than the return-focused variants, so its downside improvement is not simply the result of trading less; the risk-adjusted-return variant loses money, so nominal risk adjustment does not by itself ensure a useful training signal. Training reward Return MDD Sharpe Calmar TO IL","support":"partial"}],"reported_performance":{"strategy":"AllocFlow","sharpe":2.192,"sharpe_benchmark":null,"annual_return_pct":51.38,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":19,"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":3,"extracted_at":"2026-11-17T15:29:22Z"},"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/"}