We inspect how accurate machine learning (ML) is at forecasting realized variance of the Dow Jones Industrial Average index constituents. We compare several ML algorithms, including regularization, regression trees, and neural networks, to multiple heterogeneous autoregressive (HAR) models. ML is implemented with minimal hyperparameter tuning. In spite of this, ML is competitive and beats the HAR lineage, even when the only predictors are the daily, weekly, and monthly lags of realized variance. The forecast gains are more pronounced at longer horizons. We attribute this to higher persistence in the ML models, which helps to approximate the long memory of realized variance. ML also excels at locating incremental information about future volatility from additional predictors. Lastly, we propose an ML measure of variable importance based on accumulated local effects. This shows that while there is agreement about the most important predictors, there is disagreement on their ranking, helping to reconcile our results.

中文翻译：

---

波动率预测的机器学习方法

我们检查机器学习 (ML) 在预测道琼斯工业平均指数成分股的实际方差方面的准确度。我们将几种 ML 算法（包括正则化、回归树和神经网络）与多个异构自回归 (HAR) 模型进行比较。ML 是通过最小的超参数调整来实现的。尽管如此，ML 还是有竞争力的，并且击败了 HAR 谱系，即使唯一的预测因素是实现方差的每日、每周和每月滞后。从长远来看，预测收益更为明显。我们将此归因于 ML 模型中更高的持久性，这有助于近似实现方差的长期记忆。ML 还擅长从其他预测变量中找到有关未来波动的增量信息。最后，我们提出了一种基于累积局部效应的可变重要性的 ML 度量。这表明，虽然对最重要的预测变量达成一致，但在它们的排名上存在分歧，有助于协调我们的结果。