HARd to Beat: The Overlooked Impact of Rolling Windows in the Era of Machine Learning

By Francesco Audrino, Jonathan Chassot

Rating

1502
Battle Count: 104

Relevance

9/10
Highly relevant for volatility forecasting in quantitative trading strategies, risk management, and option pricing.

Implementation Complexity

6/10
Implementation of HAR model is straightforward, but proper tuning of ML models and extensive data processing may increase complexity.

Reproducibility

4/5
The paper provides detailed information on data sources, model specifications, and evaluation metrics. Code is not explicitly mentioned but methodology is well-described.

About this paper

Methodology: Comparative analysis. Problem types: Time Series Forecasting, Regression.

The interactive Everscope explorer (charts, battles, favorites) loads below.