Application of collaborative filtering based on deep learning in college students’ entrepreneurship project recommendation system

Abstract

With the increasing entrepreneurial activities of college students, building an effective entrepreneurial project recommendation system is crucial to stimulate innovation and improve the success rate of entrepreneurship. Traditional collaborative filtering methods have achieved some success in recommender systems. However, with the increase of data scale and the complexity of entrepreneurial projects, the effect of traditional methods is gradually limited. This study uses a data set containing a large number of entrepreneurial project data and compares the collaborative filtering model based on deep learning with traditional methods. Experimental results show that compared with traditional methods, the new model improves the recommendation accuracy by about 15% and the personalization by about 20%. This shows that deep learning has obvious advantages in processing data of large-scale entrepreneurial projects. Further data analysis also shows the training effect and generalization ability of the model. The effectiveness and robustness of the model are verified by analyzing the change trend of training loss and verification loss. Through the survey of user satisfaction, users’ satisfaction with the recommendation system based on deep learning is significantly higher than that of traditional methods.