Minimum Message Length in Hybrid ARMA and LSTM Model Forecasting

Abstract

We investigate the power of time series analysis based on a variety of information-theoretic approaches from statistics (AIC, BIC) and machine learning (Minimum Message Length) - and we then compare their efficacy with traditional time series model and with hybrids involving deep learning. More specifically, we develop AIC, BIC and Minimum Message Length (MML) ARMA (autoregressive moving average) time series models - with this Bayesian information-theoretic MML ARMA modelling already being new work. We then study deep learning based algorithms in time series forecasting, using Long Short Term Memory (LSTM), and we then combine this with the ARMA modelling to produce a hybrid ARMA-LSTM prediction. Part of the purpose of the use of LSTM is to seek capture any hidden information in the residuals left from the traditional ARMA model. We show that MML not only outperforms earlier statistical approaches to ARMA modelling, but we further show that the hybrid MML ARMA-LSTM models outperform both ARMA models and LSTM models.

Research on Stock Return Forecasting Methods based on Time Series Models

“…Among them, stock data is a typical time series data, and the theory of time series model is relatively solid and mature, so the example of using time series model to predict stock trend is more extensive. Many time series models, such as ARMA and ARIMA, can be used to predict the return rate of stocks, and the future stock price can be deduced according to the predicted return rate, so as to achieve the purpose of predicting the stock price [2][3][4][5]. So the core task of this paper is to build a model to predict stock returns.…”