The rapid development of data-driven artificial intelligence promotes the precision and personalization of college students’ career planning education. This paper analyzes career trends and job market demand through big data mining and machine learning technology, etc., to provide data support for college students’ career planning. The career planning decision-making module is analyzed in terms of both goals and processes. Strong association rules are extracted from data such as graduates’ employment situation to find the key factors affecting career planning and actual employment. Construct an accurate employment prediction model through feature engineering optimization and Stacking integrated model design to provide reference for final career planning. The method of this paper is applied to the association rule mining of actual college students’ employment data, and the accuracy of the prediction results is compared to analyze the specific correlation between academic feature attributes and career planning and actual employment. The results show that mining yields three classes of comprehensive attribute classification rules. The AUC value of this paper’s algorithm Stacking is 0.843, and the prediction results are better than the comparison algorithm. The most influential attribute on career planning and actual employment, “employment intention”, is significantly correlated at the 0.01 level. The next most influential attributes were specialty, intention to work in the region, awards, and working hours.
