We investigate whether there are predictable patterns in the dynamics of higher-order risk-neutral moments (RNMs) extracted from the market prices of Standard & Poor’s (S&P) 500 index options. To this end, we conduct a horse race among alternative forecasting models within an out-of-sample context over various forecasting horizons. We consider both a statistical and an economic setting. We find that higher RNMs can be statistically forecasted. However, only the 1-day-ahead skewness forecasts can be economically exploited. This economic significance vanishes once we incorporate transaction costs. The results have implications for the dynamics of implied volatility surfaces.