Discovering High Utility Episodes in Sequences

TL;DR

This paper introduces UMEpi, an efficient utility mining method for discovering high-utility episodes in complex event sequences, outperforming existing algorithms in accuracy and efficiency.

Contribution

The paper proposes a novel approach with tighter upper bounds and improved pruning strategies for high-utility episode mining in sequence data.

Findings

UMEpi accurately discovers all high-utility episodes.

UMEpi significantly reduces execution time and memory usage.

Experimental results outperform state-of-the-art algorithms.

Abstract

Sequence data, e.g., complex event sequence, is more commonly seen than other types of data (e.g., transaction data) in real-world applications. For the mining task from sequence data, several problems have been formulated, such as sequential pattern mining, episode mining, and sequential rule mining. As one of the fundamental problems, episode mining has often been studied. The common wisdom is that discovering frequent episodes is not useful enough. In this paper, we propose an efficient utility mining approach namely UMEpi: Utility Mining of high-utility Episodes from complex event sequence. We propose the concept of remaining utility of episode, and achieve a tighter upper bound, namely episode-weighted utilization (EWU), which will provide better pruning. Thus, the optimized EWU-based pruning strategies can achieve better improvements in mining efficiency. The search space of UMEpi w.r.t. a prefix-based lexicographic sequence tree is spanned and determined recursively for mining high-utility episodes, by prefix-spanning in a depth-first way. Finally, extensive experiments on four real-life datasets demonstrate that UMEpi can discover the complete high-utility episodes from complex event sequence, while the state-of-the-art algorithms fail to return the correct results. Furthermore, the improved variants of UMEpi significantly outperform the baseline in terms of execution time, memory consumption, and scalability.