用合成数据训练神经网络，提升少数据下的投资组合优化鲁棒性
Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training
- 用CVaR优化器生成标签，结合合成数据训练贝叶斯与确定性模型
- 在104个真实样本上实现比基准更优的收益与更低换手率
- 适合金融工程、量化投资中数据稀缺场景的稳健建模需求
本文提出一种机器学习辅助的投资组合优化框架，适用于低数据环境与市场状态突变。构建教师-学生学习流程：由条件风险价值（CVaR）优化器生成监督标签，利用真实数据与合成数据训练神经网络模型（贝叶斯与确定性）。合成数据基于因子模型与t-柯西残差生成，扩展了仅有104个标注样本的真实数据。在三类实验设置下评估四类学生模型：(i) 受控合成实验（3×5种子网格），(ii) 市场内真实评估（C2A），(iii) 跨市场泛化测试（D2A）。真实市场部署采用滚动评估协议：冻结预训练模型后，定期用近期数据微调并重置初始状态，确保稳定性同时允许有限适应。结果表明，学生模型在多个场景中可匹敌或超越CVaR教师模型，且在市场状态突变下表现更鲁棒，换手率更低。说明混合优化学习方法可有效提升数据受限环境下的投资组合构建能力。
原文摘要 · Abstract (English)
This paper proposes a machine learning assisted portfolio optimization framework designed for low data environments and regime uncertainty. We construct a teacher student learning pipeline in which a Conditional Value at Risk (CVaR) optimizer generates supervisory labels, and neural models (Bayesian and deterministic) are trained using both real and synthetically augmented data. The synthetic data is generated using a factor based model with t copula residuals, enabling training beyond the limited real sample of 104 labeled observations. We evaluate four student models under a structured experimental framework comprising (i) controlled synthetic experiments (3 x 5 seed grid), (ii) in-distribution real market evaluation (C2A) and (iii) cross-universe generalization (D2A). In real-market settings, models are deployed using a rolling evaluation protocol where a frozen pretrained model is periodically fine tuned on recent observations and reset to its base state, ensuring stability while allowing limited adaptation. Results show that student models can match or outperform the CVaR teacher in several settings, while achieving improved robustness under regime shifts and reduced turnover. These findings suggest that hybrid optimization learning approaches can enhance portfolio construction in data constrained environments
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。