Research on the prediction model of total retail sales of social consumer goods based on Monte Carlo simulation

Abstract:
The sudden outbreak of COVID-19 has quickly spread to the world, causing a major negative impact on the economy. The circulation industry is also the first to bear the brunt, the total retail sales of consumer goods plays an important role in indicating the development of the circulation industry. Based on this practical problem, this thesis analyses the characteristics of the total retail sales of social consumer goods, and proposes a method using Monte Carlo simulation to select out the optimal prediction model from three models: ARIMA model, grey model, and Long-Short Term Memory recurrent neural network, in order to provide a reference for the forecast of total retail sales of social consumer goods. The results show that the total retail sales of social consumer goods has the characteristics of an upward trend and periodic fluctuations, and the grey model has a good prediction effect on the total retail sales of social consumer goods.