Time series forecasting with SOM and local non-linear models - Application to the DAX30 index prediction

A general method for time series fore- casting is presented. Based on the splitting of the past dynamics into clusters, local models are built to cap- ture the possible evolution of the series given the last known values. A probabilistic model is used to com- bine the local predictions. The method can be applied to any time series prediction problem, but is particu- larly suited to data showing non-linear dependencies and cluster effects, as many financial series do. The method is applied to the prediction of the returns of the DAX30 index.