Research on Accurate Identification of Poor Students in Colleges Based on Big Data Analysis

In recent years, colleges have greatly expanded their enrollment and the number of college students has increased dramatically, which has greatly increased the difficulty and workload of poor student funding. It is urgent to use big data information to accurately identify which students are from poor families. In this way, the scientific nature of funding for poor students can be enhanced, and the subjective factors of democratic voting and identification of personnel can be eliminated, which will make the funding work more objective and efficient. This article proposes a poor student identification model based on student family information and big data analysis of campus card consumption. We use the optimized K-means clustering analysis algorithm and big data technology to establish a poor student identification model based on cluster analysis, which is a good way to help schools identify poor students. The experimental results show that the model has a high accuracy rate, and it is of great significance for standardizing the funding of poor students and the targeted poverty alleviation policies of education.