Intelligent average utility pattern analysis using pre-large concept in dynamic stream data

Recent studies on high average utility pattern analysis aim to extract patterns from quantitative data considering the pattern length in incremental environments. However, traditional methods have the limitation that the pattern expansion process is conducted whenever incremental data occur. The pre-large concept is a technique that addresses this by classifying patterns and leveraging them to reduce re-scan and pattern expansion operations with a re-scan condition. In this paper, a novel approach is proposed for analyzing high average utility patterns leveraging the framework of the pre-large concept with the tight re-scan condition. Specifically, the proposed approach adopts a newly proposed tight re-scan condition combined with effective pattern tree management. This approach manages the occurrence of the pattern expansion process more efficiently than state-of-the-art methods and reduces redundant computations while extracting results through the average utility of each pattern. Comprehensive experiments on real and synthetic datasets demonstrate that the proposed method is superior to other comparison methods regarding runtime and scalability while exhibiting completeness with competitive memory usage. Furthermore, the sensitivity tests indicate that the proposed approach maintains the most stable runtime performance under varying thresholds, and the case study under concept drift tests demonstrates its superior scalability, showing its applicability compared to the state-of-the-art approach.