Multiple forecasting using local approximation

摘要

In this paper, two local approximation techniques for prediction are explored. First, a pattern recognition technique called Pattern Modelling and Recognition System (PMRS) is explored for making multiple forecasts. We then describe a single nearest-neighbour-based prediction system for multiple forecasting. Both models are based on using local neighbourhoods in data for making prediction. Multiple prediction profiles are generated and analysed for four-time series data. These multiple forecasts define a predicted behavioural profile of given univariate systems. The predicted profiles are compared against the actual behaviour of the studied systems on a number of proposed error measures. The results show that local approximation used in the two models for making multiple forecasts is an important method of profiling the true behaviour of univariate systems.