Correlation Analysis of Computer Curriculums Based on Clustering and Association Rules

The current curriculum holds great significance in the talent training program of universities, as its reasonable structure directly impacts the quality of talent development. However, the curriculum is primarily based on the expertise and experience of administrators, experts, and teachers. In light of this, this paper proposes an analysis method for curriculum scores based on clustering and association rules to address the learning situation and improvement needs of computer science and technology students within their training programs. Specifically focusing on 2018 undergraduate Curriculum scores as research objects, K-means algorithm is used to discretize grade information, and Apriori algorithm is used for data mining in order to derive association rules between curriculums in this paper. This enables us to analyze both inter-curriculum relationships and curriculum importance. The mined rules not only provide valuable reference information for designing and enhancing teaching schemes but also contribute towards optimizing professional curriculum systems. Ultimately, they play a pivotal role in improving teaching quality as well as students' learning outcomes.