Predicting Realized Variance Out of Sample: Can Anything Beat The Benchmark?

TL;DR

This paper investigates whether advanced machine learning models can outperform traditional benchmarks in predicting daily realized volatility, highlighting the importance of forecast accuracy for portfolio performance.

Contribution

It compares high-dimensional machine learning models with low-dimensional factor models in predicting daily volatility, emphasizing the impact of forecast improvements on investment outcomes.

Findings

Machine learning models offer marginal forecast error improvements.

Small forecast accuracy gains lead to significant portfolio performance benefits.

Reconsidering model training methods can enhance portfolio construction.

Abstract

The discrepancy between realized volatility and the market's view of volatility has been known to predict individual equity options at the monthly horizon. It is not clear how this predictability depends on a forecast's ability to predict firm-level volatility. We consider this phenomenon at the daily frequency using high-dimensional machine learning models, as well as low-dimensional factor models. We find that marginal improvements to standard forecast error measurements can lead to economically significant gains in portfolio performance. This makes a case for re-imagining the way we train models that are used to construct portfolios.