A bilateral employment situation prediction model for college students using GCN and LSTM.

Due to the prevailing trend of globalization, the competition for social employment has escalated significantly. Moreover, the job market has become exceedingly competitive for students, warranting immediate attention. In light of this, a novel prognostic model employing big data technology is proposed to facilitate a bilateral employment scenario for graduates, aiding college students in promptly gauging the prevailing social employment landscape and providing precise employment guidance. Initially, the focus lies in meticulously analyzing pivotal aspects of college students' employment by constructing a specialized employment platform. Subsequently, a classification model grounded in a graph convolution network (GCN) is built, leveraging big data technology to comprehensively comprehend graduates' strengths and weaknesses in the employment milieu. Furthermore, based on the outcomes derived from the comprehensive classification of college students' qualities, a college students' employment trend prediction method employing long and short term memory (LSTM) is proposed. This method supplements the analysis of graduates' employability and enables accurate forecasting of college students' employment trends. Empirical evidence substantiates that my proposed methodology effectively evaluates graduates' comprehensive qualities and successfully predicts their employment prospects. The achieved F-values, 82.45% and 69.89%, respectively, demonstrate the efficacy of anticipating the new paradigm in graduates' dual-line employment.