Forecasting of consumer price index using the ensemble learning model with multi-objective evolutionary algorithms: Preliminary results

Time series forecasting is paid a considerable attention of the researchers. At present, in the field of machine learning, there are a lot of studies using an ensemble of artificial neural networks to construct the model for time series forecasting in general, and consumer price index (CPI) forecasting, in particular. However, determining the number of members of an ensemble is still debatable. This paper proposes the way of constructing a model for CPI forecasting and designing a multi-objective evolutionary algorithm in training neural networks ensembles in order to increase the diversity of the population. Two objectives of the training problem include: Mean Sum of Squared Errors and diversity. We experimented the model on three data sets and compared methods. The experimental results showed that the proposed model produced better in investigated cases.