Cross-Domain Recommendation System Based on Tensor Decomposition for Cybersecurity Data Analytics

In the context of personalization e-commerce cyberspace based on massive data, the traditional single-domain recommendation algorithm is difficult to adapt to cross-domain information recommendation service. Collaborative filtering is a simple and common recommendation algorithm, but when the target domain is very sparse, the performance of collaborative filtering algorithm will seriously degrade. Cross domain recommendation is an effective way to solve this problem because it is made by means of the auxiliary data domain associated with the target data domain. Most of the existing cross-domain recommendation models are based on two-dimensional rating matrix, and much other dimension information is lost, which leads to a decrease in recommended accuracy. In this paper, we propose a cross-domain recommendation method based on tensor decomposition, which can reduce the sparseness of data and improve the diversity and accuracy. It extracts the scoring patterns in different fields to fill the vacancy value in the target domain by transfer learning method. Many experiments on three public real data sets show that the proposed model's recommendation accuracy is superior to some of the most advanced recommendation models. It can be applied to large-scale cross-domain information recommendation service and cybersecurity data analytics.