An Empirical Study on the Impact of Supply Chain Finance on the Performance of the Automobile Industry in the Post-covid-19 Era

Abstract

Background: In recent years, trade on credit has become increasingly common around the world, exposing companies in the supply chain to significantly increased financial risk due to extended billing periods. As an innovative financing model, supply chain finance (SCF) has received a lot of attention. background: The exhaust gas of traditional fuel vehicles is a major cause of environmental problems such as air pollution and global warming. In order to promote the low-carbon development of the energy system and contribute to the realization of carbon peaking and carbon neutrality, new energy electric vehicles quickly become an important part of the global new energy strategy by virtue of low-carbon, environmental protection, high-performance and other advantages. In recent years, China has attached great importance to breaking through the core technology of electric vehicles and improving product performance, and issued relevant policies to encourage and support the development of the industry. As a result, the industrialization of new energy charging vehicles has been accelerating. At the same time, the charging infrastructure of electric vehicles is also developing rapidly. The charging infrastructure is a variety of charging and changing facilities that provide energy supply for electric vehicles, and is an indispensable supporting infrastructure for the development of electric vehicles. The charging management platform needs to conduct power dispatching by region, so understanding the charging behavior of users can not only help relevant enterprises to develop business strategies, but also guide the infrastructure construction of the electric vehicle industry. Objective: The goal of this work is to examine the impact of supply chain finance on the performance of the automobile industry in the post-covid-19 era. objective: Forecasting the trading electricity can help relevant departments or enterprises better understand the charging behavior and habits of users, and further adjust and optimize the power supply, service and construction. Methods: After an in-depth understanding of the relevant theoretical literature, two models of inquiry are established in this paper, and the relevant data are collected from the CSMAR database for a sample of some enterprises in the automotive industry in the listed market, followed by an empirical analysis using the Stata 16.0. Then, the fixed effects model (FEM) and difference-indifference model (DID) are used to test the hypothesis. Results: The results show a significant impact of supply chain finance on the performance of automobile firms. It is effective in improving the flow of funds and contributes to the performance of enterprises in the automotive industry. Conclusion: In the context of the pandemic, supply chain finance can effectively help enterprises reduce the risk of bankruptcy due to capital rupture and provide a guarantee for the sustainable development of automobile industry enterprises. conclusion: Forecasting the trading electricity can help relevant departments or enterprises better understand the charging behavior and habits of users, and further adjust and optimize the power supply, service and construction. Based on the actual transaction electricity data of Hubei Province, the following conclusions are drawn through the example simulation: the electric vehicle industry is still in the development stage. Based on the analysis of the existing data, the LSTM-SVR algorithm proposed can effectively predict the fluctuation of the charging amount, and the deviation between the predicted value and the actual value is small. Therefore, the model can be used as a charging capacity prediction method to provide a reference basis for the electric vehicle charging management platform to conduct power control strategies, and help accelerate the construction of a charging infrastructure system with reasonable distribution and perfect functions; Understanding the charging habits of users, optimizing the charging configuration and improving the service system are conducive to improving the satisfaction of electric vehicle users and promoting the healthy, rapid and sustainable development of the industry. other: At present, research on charging prediction of electric vehicles is emerging in endlessly. Literature proposed an electric vehicle load prediction model that considers the time period of possible charging of electric vehicles, and studies such factors as daily mileage, user charging habits and possible charging time. Literature simulates the driving, parking and charging behaviors of a large number of electric vehicles in different areas by describing the user's travel habits, so as to obtain the charging loads of electric vehicles in different areas. Literature considered the influence of key meteorological factors and combined with time convolution network to predict charging load. The literature also considers the daily travel mileage, the scale and type of electric vehicles, the user's charging habits and other factors that affect the charging capacity of electric vehicles to predict the charging load of electric vehicles. In addition, there are also electric vehicle load forecasting models based on machine learning, deep learning and other theories, which also have some reference significance.In general, the current research on electric vehicle charging prediction mainly focuses on the charging load prediction, while the research on charging capacity prediction is less. The amount of electric vehicle charging is closely related to the construction of charging facilities, charging network planning, etc. Therefore, in the current rapid development stage of electric vehicles, the prediction of charging amount has certain practical application value. Therefore, this paper mainly studies the prediction of electric vehicle charging capacity. Charging quantity prediction is a time series prediction problem, and the classic time series prediction model ARIMA is usually used. With the upgrading of machine hardware, machine learning and deep learning technologies are also more widely used in time series prediction. Combined with the electric vehicle trading energy data in Hubei Province, support vector machine (SVM), long short term memory (LSTM) and support vector regression (SVR) are used to predict the trading energy, which is of great significance to the operation of the charging management platform.