Top Favorite Probabilistic Products Queries

Xu Zhou, Kenli Li, Guoqing Xiao, Yantao Zhou, Keqin Li

IEEE Transactions on Knowledge and Data Engineering · 2016 · 49 citations · 25 references

Concepts

TL;DR

Product selection under uncertainty has been addressed by probabilistic dynamic skyline queries, but these require a threshold, focus only on high‑probability objects, and yield unstable results. This study introduces an uncertain dynamic skyline query and a top‑k favorite probabilistic products query to overcome the limitations of existing PDS queries. We develop pruning strategies and efficient algorithms, including a parallelized TFPP algorithm, to compute the UDS and TFPP queries. Experiments demonstrate that the proposed algorithms are efficient and effective across diverse settings.

Abstract

With the development of the economy, products are significantly enriched, and uncertainty has been their inherent quality. The probabilistic dynamic skyline (PDS) query is a powerful tool for customers to use in selecting products according to their preferences. However, this query suffers several limitations: it requires the specification of a probabilistic threshold, which reports undesirable results and disregards important results; it only focuses on the objects that have large dynamic skyline probabilities; and, additionally, the results are not stable. To address this concern, in this paper, we formulate an uncertain dynamic skyline (UDS) query over a probabilistic product set. Furthermore, we propose effective pruning strategies for the UDS query, and integrate them into effective algorithms. In addition, a novel query type, namely the top <inline-formula><tex-math notation="LaTeX">$k$</tex-math> </inline-formula> favorite probabilistic products (TFPP) query, is presented. The TFPP query is utilized to select <inline-formula> <tex-math notation="LaTeX">$k$</tex-math></inline-formula> products which can meet the needs of a customer set at the maximum level. To tackle the TFPP query, we propose a TFPP algorithm and its efficient parallelization. Extensive experiments with a variety of experimental settings illustrate the efficiency and effectiveness of our proposed algorithms.

References

25