arXiv:2608.23393q-fin.PMcs.LG2026-08

用梯度提升树构建收益最优投资组合,直接优化长期增长率。

KellyBoost: Growth-Optimal Portfolio Construction with Gradient-Boosted Trees

  • 用XGBoost建模,输出为资产配置权重,目标函数为负对数增长速率。
  • 训练损失直接对应长期财富增长,实现理论最优的凯利配置。
  • 提供闭式导数与海森矩阵,可精确优化,适合量化交易研究者使用。

KellyBoost 是一个单个多输出 XGBoost 模型,其 softmax 输出即为投资组合权重。以各资产持有期收益率向量 y 为输入,训练损失定义为 -log(1 + w^T y),即负对数财富增长率。因此,拟合模型即为在给定特征条件下,基于特征的生长最优(凯利)资产配置。该目标函数为精确表达式而非代理目标,我们推导出其梯度、解析的对角海森矩阵及完整海森矩阵,并通过有限差分验证。此外,项目提供无依赖的参考实现引擎。

原文摘要 · Abstract (English)

KellyBoost is a single multi-output XGBoost model whose softmax output is the portfolio: with y the vector of per-asset holding-period returns, the training loss is - log(1 + w y), the negative log growth rate, so the fitted model is the growth-optimal (Kelly) allocation conditioned on the features. The objective is exact rather than a surrogate: we derive the gradient, the analytic diagonal Hessian and the full Hessian in closed form, verify them by finite differences, and ship a dependency-free reference engine.

投资组合机器学习强化学习贝叶斯优化

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。