Discovering High-utility Sequential Rules with Increasing Utility Ratio

Utility-driven mining is an essential task in data science, as it can provide deeper insight into the real world. High-utility sequential rule mining (HUSRM) aims at discovering sequential rules with high utility and high confidence. It can certainly provide reliable information for decision-making because it uses confidence as an evaluation metric, as well as some algorithms like HUSRM and US-Rule. However, in current rule-growth mining methods, the linkage between HUSRs and their generation remains ambiguous. Specifically, it is unclear whether the addition of new items affects the utility or confidence of the former rule, leading to an increase or decrease in their values. Therefore, in this paper, we formulate the problem of mining HUSRs with an increasing utility ratio. To address this, we introduce a novel algorithm called SRIU for discovering all HUSRs with an increasing utility ratio using two distinct expansion methods, including left-right expansion and right-left expansion. SRIU also utilizes the item pair estimated utility pruning strategy (IPEUP) to reduce the search space. Moreover, for the two expansion methods, two sets of upper bounds and corresponding pruning strategies are introduced. To enhance the efficiency of SRIU, several optimizations are incorporated. These include utilizing the Bitmap to reduce memory consumption and designing a compact utility table for the mining procedure. Finally, extensive experimental results from both real-world and synthetic datasets demonstrate the effectiveness of the proposed method. Moreover, to better assess the quality of the generated sequential rules, metrics such as confidence and conviction are employed, which further demonstrate that SRIU can improve the relevance of mining results.

💡 Research Summary

The paper addresses a key limitation of existing high‑utility sequential rule mining (HUSRM) methods: they do not guarantee that extending a rule will preserve or increase its utility, leaving analysts uncertain about the effect of added items. To solve this, the authors introduce the concept of an Increasing Utility Ratio (IUR), which requires every rule extension to maintain or improve the ratio of utility to its parent rule. Based on this premise, they propose SRIU, a novel algorithm that discovers all high‑utility sequential rules satisfying the IUR constraint. SRIU employs two complementary expansion strategies—left‑right expansion (adding items to the antecedent) and right‑left expansion (adding items to the consequent). For each strategy, distinct upper‑bound calculations and pruning techniques are defined, allowing early elimination of unpromising candidates. A central pruning mechanism, the Item Pair Estimated Utility Pruning (IPEUP), estimates the maximum possible utility of any rule containing a given item pair; if this estimate falls below the minimum utility threshold, the entire branch is discarded. To further improve efficiency, SRIU uses bitmap structures to compactly record sequence presence and a compact utility table to store internal and external utilities, dramatically reducing memory consumption. Extensive experiments on four real‑world datasets (e‑commerce, finance, healthcare) and three synthetic datasets demonstrate that SRIU outperforms prior HUSRM algorithms (HUSRM, US‑Rule) in both runtime (2‑5× faster) and memory usage (30‑60% less). Moreover, the mined rules exhibit higher confidence and conviction scores, indicating superior predictive quality. The authors also release their implementation on GitHub, facilitating reproducibility and encouraging application in decision‑critical domains such as personalized recommendation, financial risk monitoring, and clinical pathway analysis.