Forecasting by Beanplot Time Series

In this paper, we propose a new approach for the aggregation, the parameterization and the forecasting of complex time series. This approach is based on a peculiar density plot, called beanplot (Kampstra (2002)). These types of new aggregated time series can be fruitfully used when there is an overwhelming number of observations, for example in High Frequency nancial data. At the same time, they can be useful for analyzing the complex behaviour of the markets where we can discover important patterns in the long time (complex patterns of dependency over the time).