Entropy for Time Series Forecasting

In this paper, we present the exploitation of a method to extract information from microscopic samples of time series data in order to provide a representation of optimized stability to a chaotic system [1]. The main goal of this approach is to predict the dynamics of a time series and therefore develop optimized forecasting algorithms. First, we study how to increase the predictability of a system and second, we develop a Deep Learning Algorithm, namely an LSTM, that can recognize patterns in sequential data and accurately predict the future behaviour of a time series.