Dynamic Information Mining Based Vaccine Distribution Strategy

Abstract

Vaccination is essential for preventing epidemics likes COVID-19. Rational vaccine distribution can greatly improve vaccination efficiency and reduce costs. In this paper, to predict the number of future vaccinations, we utilize ARIMA model on the total number of new coronavirus vaccinations in China for a period. Based on the model, we propose a vaccine distribution method that is composed of two distribution strategies with different characteristics, namely “proximity based vaccine distribution” and “transfer based vaccine disritbution Specifically, we propose a hierarchical vaccination serving communities model to obtain the serving pressures, and construct a first order Marcov chain to explore the importance of different vaccination sites to decide the dynamic distribution with consideration of the rules based on some practical factors. Extensive experiments including two cities in China show that the proposed model can flexibly and effectively adapt to cities with different conditions.