Evolutionary Algebraic Forecasting: Evolutionary algorithms for algebraic forecasting of short time series

DOI: 10.5176/2251-2179_ATAI6

Authors: Minvydas Ragulskis, Rita Palivonaite and Zenonas Navickas

Abstract:

A new short-term time series forecasting method based on the identification of skeleton algebraic sequences is proposed in this paper. The concept of the rank of the Hankel matrix is exploited to detect a base fragment of the time series and to extrapolate the model of the process into future. Evolutionary algorithms are used to remove the noise, to identify the skeleton algebraic sequence and to balance the forecast with the smoothed moving average estimate of the time series. Numerical experiments with an artificially generated and real-world time series are used to illustrate the functionality of the proposed technique.

Keywords: series forecasting; evolutionary algorithms; algebraic sequence)