DBNCF: Personalized Courses Recommendation System Based on DBN in MOOC Environment

With the rapid development of MOOC platform, MOOC resource recommendation technology is emerging to improve the learner's learning efficiency. The traditional collaborative filtering resource recommendation technique is ineffective when dealing with sparse data and cannot accurately handle the high dimension attributes of online learning users, which result in low efficiency of resource recommendation. In order to solve this problem, this paper proposes a personalized recommendation system based on DBN in MOOC environment, which utilizes the high performance of DBN in function approximation, feature extraction, prediction classification and other aspects. It combines MOOC platform user - course feature vector to mine the user's course interests. Meanwhile, it uses the score of courses as the class label of DBN supervised learning. Through unsupervised pre-training and supervised feedback fine-tuning, the DBN recommendation model training can be achieved. The experiment was carried out in the real MOOC platform "starc", and was compared with several traditional recommendation methods. The experimental results show that the DBNCF is more efficient than the traditional cooperative filtering method.