We set up an early warning system for financial crises based on the Random Forrest approach. We use a novel set of predictors that comprises financial development indicators (e.g. levels of credit to GDP ratio) in addition to conventional imbalances measures (e.g. credit gaps). The evaluation of the model is conducted using a three-step procedure (i.e. training, validation and testing sub-samples). The results indicate that combining financial imbalances and financial development indicators helps to improve the out-of-sample accuracy of the early warning system.