Abstract: We investigate whether there are predictable patterns in the dynamics of higher order risk-neutral moments extracted from the market prices of 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 risk-neutral moments can be statistically forecasted. However, only the one-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.