We investigate the performance of non-linear return prediction models in the high complexity regime, i.e., when the number of model parameters exceeds the number of observations. We document a “virtue of complexity”: Return prediction R2 and optimal portfolio Sharpe ratio generally increase with model parameterization in all asset classes that we study (US equities, international equities, bonds, commodities, currencies, and interest rates). The virtue of complexity is present even in extremely data-scarce environments, e.g., for predictive models with less than twenty observations and tens of thousands of predictors. The empirical association between model complexity and out-of-sample model performance exhibits a striking consistency with theoretical predictions.

中文摘要：

我们研究了非线性回报预测模型在高复杂性条件下的表现，即模型参数数量超过观测数据数量时的表现。我们发现了 "复杂性的优点"：在我们研究的所有资产类别（美国股票、国际股票、债券、商品、货币和利率）中，收益预测 R2 和最优投资组合夏普比率通常会随着模型参数化的增加而增加。即使在数据极其稀缺的环境中，复杂性的优势也是存在的，例如，对于观测数据不足 20 个、预测因子数以万计的预测模型。模型复杂性与样本外模型性能之间的经验关联与理论预测惊人地一致。

嘉宾介绍：

周康颖，耶鲁大学管理学院金融专业在读博士生，师从Bryan Kelly教授。本科毕业于18luck新利电竞经济学院。硕士毕业于芝加哥大学金融数学专业，师从修大成教授。曾工作于Bloomberg (Chief Technology Office)。研究方向为实证资产定价（empirical asset pricing），成果发表于Journal of Finance。