Research on Poverty Alleviation in China Based on Big Data in the Context of COVID-19

Abstract

Objectives: In order to alleviate the impact of COVID-19 on China's poverty alleviation work, this paper proposes
a performance evaluation method and a recommendation algorithm for poverty indicator system suitable for
China's national conditions based on big data technology. Methods: The evaluation method combines the precise
advantages of Bayesian classifier and the full-volume processing characteristics of big data to comprehensively
evaluate the past poverty alleviation achievements. The recommendation algorithm takes the poverty alleviation
data over the years as the research object and realizes the construction method of the indicator system in the
relative poverty stage. Results: The comparison with Pearson's correlation coefficient shows that the new
evaluation method has more accurate confidence calculation ability. And compared with the classic ALS
recommendation algorithm, the new recommendation algorithm has a more scientific and reasonable
recommendation effect. Conclusions: Finally, the paper proposes relevant suggestions for the next stage of policy
formulation, proves that medical and health conditions play an important role in supporting poverty alleviation.