C4.5 crossover algorithm based on mapreduce in university big data analysis

Abstract

With the continuous development of digitization and informationization, students' data generated by various kinds of application systems in colleges and universities is also accelerating. A big data environment of colleges and universities has been formed. The data contains a wealth of information that requires new storage and analysis tools for processing. Therefore, in this paper, big data processing platform Hadoop is used to analyze college big data, and C4.5 cross-improvement algorithm is proposed based on the low efficiency and over-fitting of decision tree C4.5 algorithm, and then verified in student grants data Improve the feasibility of the algorithm. Finally, the validity of the improved algorithm is verified from different evaluation criteria. The experimental results show the effectiveness and feasibility of the improved algorithm proposed in this paper, which provides a new idea and method for big data analysis in colleges and universities.