Predicting Entrepreneurial Intention of Students: Kernel Extreme Learning Machine with Boosted Crow Search Algorithm

College students are the group with most entrepreneurial vitality and potential. How to cultivate their innovative ability is one of important urgent issues facing this current social development. This paper proposes a reliable, intelligent prediction model intentions, providing theoretical support for guiding college students’ positive intentions. The mainly uses improved crow search algorithm (CSA) optimize kernel extreme learning machine (KELM) feature selection (FS), namely CSA-KELM-FS, study intention. To obtain best fitting key features, gradient rule, local escaping operator, levy flight mutation (GLL) mechanism introduced enhance CSA (GLLCSA), FS used extract features. verify performance proposed GLLCSA, it compared eight other state-of-the-art methods. Further, GLLCSA-KELM-FS five methods have been predict intentions 842 from Wenzhou Vocational in Zhejiang, China, past years. results show that can correctly intention an accuracy rate 93.2% excellent stability. According model, factors affecting student’s major studied, campus innovation, entrepreneurship practice experience, personality. Therefore, expected be effective tool predicting