Research on Recommendation of Big Data for Higher Education Based on Deep Learning

Abstract

To improve the recommendation accuracy of educational resources, an intelligent recommendation method based on autoencoder has been proposed by combining intelligent recommendation algorithm and autoencoder. The method uses the dimension reduction advantage of autoencoder to obtain the required feature vector. Then, the prediction score is utilized to recommend educational resources. Finally, it is verified from the algorithmic and system perspective. The results show that this recommendation method is the most efficient method. The efficiency on the dataset is 0.90, respectively. Furthermore, it can score different recommended articles, and the recommendation of different educational resources is realized.