Search

How to analyze and predict the consumption behavior of Chinese residents is of great significance based on the existing consumption theory research and the actual situation in China. This study studies the factors influencing the consumption of urban and rural residents in China through factor analysis and builds a model of urban and rural residents' consumption expenditure based on BP neural network. At the same time, through the data collection, the consumption data of urban and rural residents in China from 1986 to 2017 were collected. The BP neural network prediction model was used to predict the consumption expenditure of urban and rural residents, and the absolute error and relative error were obtained. In addition, this study establishes a combined forecasting model based on Lasso regression analysis and BP neural network to predict the consumption expenditure of urban and rural residents and compares its prediction results with BP neural network prediction model. The research shows that the combined prediction model based on Lasso regression analysis and BP neural network comprehensively surpasses BP neural network prediction model in prediction accuracy, and it has certain effectiveness and puts forward practical suggestions, which provides theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

This paper examines the dynamical impact of market wide liquidity on the volatility by using the Markov switching-regime approach on the Heterogeneous Autoregressive model of the realized range-based volatility (MS-HAR-RRV-LIQ). First, based on the simple partition of the liquidity measures by their historical means, we find the impact of the market liquidity on the realized range-based volatility (RRV) is non-linear with significantly stronger when the market is fluctuating. Second, by utilizing the method of Markov regimes switching, we find that in sample results, the impact of market liquidity on RRV is dynamics with much stronger when the market is fluctuating. In addition, the impact of liquidity on RRV are persistent for both the fluctuating state and the stable state, which indicate that the impact of liquidity on volatility would remain in its original state unless there are major economic events. Third, in order to eliminate the hidden information of volatility in liquidity measures, we further decompose the liquidity measures to obtain the volatility-adjusted liquidity, and find that the impact of liquidity driven by the component of liquidity uncorrelated with volatility on market volatility is also dynamics with much stronger when the market is fluctuating. Finally, out-of-sample results suggest that the models of HAR-RRV-LIQ and their corresponding volatility-adjusted liquidity models with regimes switching can increase the forecasting ability significantly than those without regime switching. • This paper examines the dynamical impact of market wide liquidity on volatility. • The impact of the market wide liquidity on RRV is non-linear. • The impact of market wide liquidity on RRV is dynamics. • Our proposed models can increase the forecasting ability significantly. [ABSTRACT FROM AUTHOR]