面向目标的量化投资：一种用于自动合成交易策略流水线的规范驱动框架
Objective-oriented quantitative investment: A specification-driven framework for automated synthesis of trading strategy pipelines
浏览论文内容
中文总结 AI 辅助
本文提出面向目标的量化投资框架OOQI，将投资者意图形式化为规范，通过编译器合成策略流水线，实验显示其比结果导向选择更能满足投资者要求，仅付出小幅分数成本。
中文摘要 AI 辅助
自动化量化研究已取得显著进展，但现有系统均回答同一问题：哪个策略在标量指标上得分最高？本文认为该问题不够全面。专业投资者并非要求“最高回报”，而是要求一种目标属性——不受风格敞口影响的纯选股阿尔法、在单边市场下跌中具备韧性、符合换手率和容量预算。本文将现有范式称为“结果导向”，并提出面向目标的量化投资（Objective-Oriented Quantitative Investment, OOQI）：一种规范驱动框架，其中（i）整个策略流水线被建模为可互换模块的类型化设计空间，带有显式接口契约（在参考实例化中有8.85×10^8种组合）；（ii）投资者意图被形式化为策略概况规范——一种由八个需求族中可测量、可证伪的子句构成的可组合语言，具有硬/软语义和交互代数；（iii）编译器将规范转换为受限组合，并逐子句验证是否满足要求。由于在大型组合空间上的搜索会夸大表面满足度，本文开发了一种验证协议，将满足率本身视为统计对象，需根据搜索宽度、时间留存集和随机组合零模型进行缩减。对32种流水线组合的合成演示显示，结果导向选择在样本内信息比率上达到最高，却仅满足25%的规范；而规范驱动选择则100%满足规范，仅付出5.5%的分数成本。伴随的理论表明，满足度驱动的合成在一般情况下是NP难问题，但在无冲突机制中具有常数因子近似性；规范形成与组合对偶的格结构；每个子句带有拉格朗日影子价格；滚动重新认证可通过e过程随时有效。
英文摘要
Automated quantitative research has made striking progress, yet each system answers the same question: which strategy scores highest on a scalar metric? We argue this question is incomplete. Professional investors do not order "the highest return"; they order an identity--pure stock-selection alpha uncontaminated by style exposure, resilient in unilateral market declines, within turnover and capacity budgets. We call the incumbent paradigm result-oriented and propose Objective-Oriented Quantitative Investment (OOQI): a specification-driven framework in which (i) the full strategy pipeline is modeled as a typed design space of interchangeable modules with explicit interface contracts (8.85 x 10^8 assemblies in our reference instantiation); (ii) investor intent is formalized as a strategy profile specification--a composable language of measurable, falsifiable clauses from eight requirement families, with hard/soft semantics and an interaction algebra; and (iii) a compiler translates specifications into constrained assemblies and verifies satisfaction clause-by-clause. Because search over large assembly spaces inflates apparent satisfaction, we develop a verification protocol treating the satisfaction rate itself as a statistical object, subject to deflation for search width, temporal holdout, and random-assembly null models. A synthetic demonstration with 32 pipeline assemblies shows that result-oriented selection attains the top in-sample information ratio while satisfying only 25% of the specification, whereas specification-driven selection satisfies 100% of it at a 5.5% score cost. The accompanying theory shows satisfaction-driven synthesis is NP-hard in general yet constant-factor approximable in a conflict-free regime; specifications form a lattice dual to assemblies; each clause carries a Lagrangian shadow price; and rolling re-certification is anytime-valid via e-processes.
