Non-stationary financial time series forecasting based on meta-learning

Abstract

In this letter, the authors address the challenge in forecasting non-stationary financial time series by proposing a meta-learning based forecasting model equipped with a convolution neural network (CNN) predictor and a long short-term memory (LSTM) meta-learner. The model is applied to a set of short subseries which are the result of dividing a long non-stationary financial time series. As a result, a promising performance can be achieved by the proposed model in terms of making more accurate prediction than the traditional CNN predictor and auto regressive (AR)-based forecasting models in non-stationary conditions.