Quarterly GDP forecast based on coupled economic and energy feature WA-LSTM model

Abstract

Existing macroeconomic forecasting methods primarily focus on the characteristics of economic data, but they overlook the energy-related features concealed behind these economic characteristics, which may lead to inaccurate GDP predictions. Therefore, this paper meticulously analyzes the relationship between energy big data and economic data indicators, explores the coupling feature mining of energy big data and economic data, and constructs features coupling economic and energy data. Targeting the nonlinear variation coupling features in China’s quarterly GDP data and using the long short-term memory (LSTM) neural network model based on deep learning, we employ wavelet analysis technology (WA) to decompose selected macroeconomic variables and construct a prediction model combining LSTM and WA, which is further compared with multiple benchmark models. The research findings show that, in terms of quarterly GDP data prediction, the combined deep learning model and wavelet analysis significantly outperform other methods. When processing structurally complex, nonlinear, and multi-variable data, the LSTM and WA combined prediction model demonstrate better generalization capabilities, with its prediction accuracy generally surpassing other benchmark models.