Optimization Model of Employment and Entrepreneurship Guidance for University Graduates Using Credible Neural Network and Spark Big Data Technology

Abstract

China’s economy has grown significantly since the turn of the century, and its domestic situation has become more stable. The employment and employment issues that college graduates encounter across the nation, however, demonstrate the opposite tendency. The general public’s attention has turned to “difficulty in getting employment,” which has emerged as a crucial component of the overall social employment problem. Additionally, it examines the environment and elements that influence college students’ employment, such as the social, economic, and policy elements as well as the university, employer, and individual elements. This study examines the development of college students’ entrepreneurial service system by using colleges and universities as the research object and integrating theoretical analysis with empirical research. The M Apriori technique is then parallelized using a Spark and Credible neural network-based approach. This solution makes full use of Spark’s benefits based on in-memory processing and data item RDD storage by adopting data parallelism and a local rather than global strategy. The M Apriori algorithm is parallelized and ported to the Spark platform for parallelization, enhancing Spark MLlib. The simulation test and analysis are completed in the end. The study’s findings demonstrate the algorithm’s excellent accuracy, which is 8.65% greater than that of the Apriori method. Finally, the experimental findings demonstrate the effectiveness of the method used in this paper.