Find in Library

Skyline queries identify skyline points, the minimal set of data points that dominate all other data points in a large dataset. The main challenge with skyline queries is executing the skyline query in the shortest possible time. To address and solve skyline query performance issues, we propose a decision tree-based method known as the <italic>decision tree-based comparator</italic> (<italic>DC</italic>). This method minimizes unnecessary dominance tests (i.e., pairwise comparisons) by constructing a decision tree based on the dominance testing. <italic>DC</italic> uses dominance relations that can be obtained from the decision rules of the decision tree to determine incomparability between data points. <italic>DC</italic> can also be easily applied to improve the performance of various existing skyline query methods. After describing the theoretical background of <italic>DC</italic> and applying it to existing skyline queries, we present the results of various experiments showing that <italic>DC</italic> can improve skyline query performance by up to 23.15 times.