Multi-category item recommendation using neighborhood associations in trust networks
Feng Xia, Haifeng Liu, Nana Yaw Asabere, Wei Wang, Zhuo Yang · 2014
This paper proposes a novel recommendation method called RecDI. In the multi-category item recommendation domain, RecDI is designed to combine user ratings with information involving user's direct and indirect neighborhood associations. Through relevant benchmarking experiments on two real-world datasets, we show that RecDI achieves better performance than other traditional recommendation methods, which demonstrates the effectiveness of RecDI.