Abstract:
We find that climate-related risks forecast the intraday data-based realized volatility of exchange rate returns of eight major fossil fuel exporters (Australia, Brazil, Canada, Malaysia, Mexico, Norway, Russia, and South Africa). We study several metrics capturing risks associated with climate change, derived from data directly on variables such as, for example, abnormal patterns of temperature. We control for various other moments (realized skewness, realized kurtosis, realized upside and downside variance, realized upside and downside tail risk, and realized jumps) and estimate our forecasting models using random forests, a machine learning technique tailored to analyze models with many predictors.
