Minimum Message Length in Hybrid ARMA and LSTM Model Forecasting

• Published in: Entropy (Basel, Switzerland) Switzerland), 2021-11, Vol.23 (12), p.1601
• Main Authors: Fang, Zheng, Dowe, David L, Peiris, Shelton, Rosadi, Dedi
• Format: Article
• Language: English
• Subjects: Autoregressive moving-average models; Bayesian statistics; Deep learning; Economic analysis; Forecasting; Information theory; long short-term memory; minimum message length; Model accuracy; Modelling; neural network; Neural networks; Time series; Trends
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e23121601

Modeling and analysis of time series are important in applications including economics, engineering, environmental science and social science. Selecting the best time series model with accurate parameters in forecasting is a challenging objective for scientists and academic researchers. Hybrid models combining neural networks and traditional Autoregressive Moving Average (ARMA) models are being used to improve the accuracy of modeling and forecasting time series. Most of the existing time series models are selected by information-theoretic approaches, such as AIC, BIC, and HQ. This paper revisits a model selection technique based on Minimum Message Length (MML) and investigates its use in hybrid time series analysis. MML is a Bayesian information-theoretic approach and has been used in selecting the best ARMA model. We utilize the long short-term memory (LSTM) approach to construct a hybrid ARMA-LSTM model and show that MML performs better than AIC, BIC, and HQ in selecting the model-both in the traditional ARMA models (without LSTM) and with hybrid ARMA-LSTM models. These results held on simulated data and both real-world datasets that we considered.We also develop a simple MML ARIMA model.