Abstract
This paper evaluates the performance of various factor models with firm‐specific variables in forecasting correlation matrices at the German stock market. We investigate forecasts of correlations for a comprehensive sample and a sample of blue chips and analyse the impact of stock market crashes on the forecasting accuracy. Our empirical results show that the multi‐factor models do not generally produce better forecasts than ‘naive’ models. Specifically, the traditional industry mean model significantly outperforms all other techniques in most of the time periods.