期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：2
页码：662-667
语种：English
出版社：Ayushmaan Technologies
摘要：Recent years and many techniques have been proposed to improve the recommendation quality. However, in most cases, new techniques are designed to improve the accuracy of recommendations, whereas the recommendation diversity has often been overlooked. In particular, we showed that, while ranking recommendations according to the predicted rating values (which is a de facto ranking standard in recommender systems) provides good predictive accuracy, it tends to perform poorly with respect to recommendation diversity. Therefore, in this paper, we proposed a number of recommendation ranking techniques that can provide significant improvements in recommendation diversity with only a small amount of accuracy loss. In addition, these ranking techniques offer flexibility to system designers, since they are parameterizable and can be used in conjunction with different rating prediction algorithms (i.e., they do not require the designer to use only some specific algorithm). They are also based on scalable sorting based heuristics and, thus, are extremely efficient. We provide a comprehensive empirical evaluation of the proposed techniques and obtain consistent and robust diversity improvements across multiple real-world datasets and using different rating prediction techniques. This work gives rise to several interesting directions for future research. In particular, additional important item ranking criteria should be explored for potential diversity improvements. This may include consumeroriented or manufacturer oriented ranking mechanisms, depending on the given application domain, as well as external factors, such as social networks. Also, as mentioned earlier, optimization-based approaches could be used to achieve further improvements in recommendation diversity, although these improvements may come with a (possibly significant). Increase in computational complexity. Moreover, because of the inherent tradeoff between the accuracy and diversity metrics, an interesting research direction would be to develop a new measure that captures both of these aspects in a single metric.
