{"paper_id":"2412.03038","title":"MILLION: A General Multi-Objective Framework with Controllable Risk for Portfolio Management","authors":["Liwei Deng","Tianfu Wang","Yan Zhao","Kai Zheng"],"paper_date":"2024-12-04","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2412.03038v1","page_url":"https://thequant.space/flowcharts/million-a-general-multi-objective-framework-with-controllab/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes MILLION, a general multi‑objective deep‑learning framework with controllable risk for portfolio management, consisting of a return‑related maximization phase and a risk‑control phase.","quote":"we propose a general Multi-objectIve framework with controLLable rIsk for pOrtfolio maNagement (MILLION)","summary":"Portfolio management is an important yet challenging task in AI for FinTech, which aims to allocate investors’ budgets among different assets to balance the risk and return of an investment. In this study, we propose a general Multi-objectIve framework with controLLable rIsk for pOrtfolio…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Assume we have a set of portfolios whose return rates are the same for the interpolation analysis.","type":"model","stated":"explicit","quote":"Assume we have a set of portfolios {𝒃1𝑡, 𝒃2𝑡, · · · , 𝒃𝑖𝑡, · · · } whose return rates are the same."},{"assumption":"A holding period is the minimum time unit to invest an asset, and the investment horizon is divided into non‑overlapped periods of fixed length (e.g., one day).","type":"market","stated":"explicit","quote":"A holding period is the minimum time unit to invest an asset. We follow previous studies that divide the whole investment period into multiple non‑overlapped holding periods with fixed length, such as one day or one month."}]},"datasets":{"status":"available","items":[{"name":"NAS100","provider":null,"kind":"market-prices","access":"unknown","period":"2009/01/01-2020/02/01 (train) / 2020/02/","universe":null,"quote":"NAS100 2009/01/01-2020/02/01 2020/02/01-2021/01/01 78"},{"name":"DOW30","provider":null,"kind":"market-prices","access":"unknown","period":"2009/01/01-2019/02/01 (train) / 2019/02/","universe":null,"quote":"DOW30 2009/01/01-2019/02/01 2019/02/01-2020/01/01 28"},{"name":"Crypto10","provider":null,"kind":"crypto-onchain","access":"unknown","period":"2018/08/02-2021/07/01 (train) / 2021/07/","universe":null,"quote":"Crypto10 2018/08/02-2021/07/01 2021/07/01-2023/10/32 10"}],"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":"Transaction cost (𝑐𝑡) in Equation 4 is set to 0","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"Transaction cost (𝑐𝑡) in Equation 4 is set to 0","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"MILLION consistently achieves the best performance in return‑related metrics such as APR, ASR, and ACR across three real‑world datasets.","kind":"performance","quote":"our proposed MILLION framework consistently achieves the best performance in terms of return‑related metrics such as APR, ASR, and ACR."},{"finding":"The portfolio improvement method outperforms the interpolation method, even when no predicted return rates are used.","kind":"performance","quote":"Improvement consistently outperforms Interpolation, even in scenarios where there are no predicted return rates to guide optimization."},{"finding":"MILLION shows comparable training times to predict‑then‑optimize algorithms and is faster than RL‑based methods.","kind":"performance","quote":"MILLION demonstrates comparable training times to predict‑then‑optimize algorithms and outperforms RL‑based methods in terms of speed."},{"finding":"As the specified risk level increases, both realized ASR and AVOL increase, confirming the fine‑grained risk control capability.","kind":"theoretical","quote":"as specified risk increases, both realized ASR and AVOL simultaneously increase."},{"finding":"Risk‑constrained portfolios can achieve higher ASR than portfolios optimized solely for Sharpe ratio, e.g., LR with risk 5e‑5 yields ASR > 1.5 on DOW30.","kind":"performance","quote":"constraining LR’s risk to 5e-5 results in an ASR exceeding 1.5, surpassing the 1.43 ASR achieved through maximizing the Sharpe ratio alone"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"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/LIWEIDENG0830/MILLION","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":"2026-11-14T17:50:56Z"},"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/"}