A Novel Multi-Factor Three-Step Feature Selection and Deep Learning Framework for Regional GDP Prediction: Evidence from China

Gross domestic product (GDP) is an important index reflecting the economic development of a region. Accurate GDP prediction of developing regions can provide technical support for sustainable urban development and economic policy formulation. In this paper, a novel multi-factor three-step feature selection and deep learning framework are proposed for regional GDP prediction. The core modeling process is mainly composed of the following three steps: In Step I, the feature crossing algorithm is used to deeply excavate hidden feature information of original datasets and fully extract key information. In Step II, BorutaRF and Q-learning algorithms analyze the deep correlation between extracted features and targets from two different perspectives and determine the features with the highest quality. In Step III, selected features are used as the input of TCN (Temporal convolutional network) to build a GDP prediction model and obtain final prediction results. Based on the experimental analysis of three datasets, the following conclusions can be drawn: (1) The proposed three-stage feature selection method effectively improves the prediction accuracy of TCN by more than 10%. (2) The proposed GDP prediction framework proposed in the paper has achieved better forecasting performance than 14 benchmark models. In addition, the MAPE values of the models are lower than 5% in all cases.

Covid-19's impact on China's economy: a prediction model based on railway transportation statistics.

The outbreak of Covid-19 in China during the Spring Festival of 2020 has changed life as we knew it. To explore its impact on China's economy, we analyse the daily railway passenger volume data during the Spring Festival travel rush and establish two RegARMA models to predict GDP in the first quarter. The models forecast China might lose 4.8 trillion yuan in the first quarter of 2020 due to Covid-19, an expected decrease of 20.69 percent (year-on-year drop 15.60 percent). However, comparing our forecast GDP without Covid-19 (23.2 trillion yuan) with the real GDP (20.65 trillion yuan), there is a smaller drop of 2.55 trillion yuan, a gap of 12.35 percent. The reason for this overestimation is that some positive factors, including macro-control policies, are neglected in these models. With the global spread of Covid-19, China should adopt a policy of focusing on balancing both domestic and external affairs against the instability of the world economy.