Flexibly Mining Better Subgroups
This work addresses a domain-specific problem in data mining for researchers and practitioners, offering an incremental improvement over existing binning strategies.
The paper tackled the challenge of discovering high-quality subgroups from numerical attributes by proposing FLEXI, an optimal binning method tailored for subgroup discovery, which outperformed state-of-the-art approaches with up to 25 times improvement in subgroup quality.
In subgroup discovery, also known as supervised pattern mining, discovering high quality one-dimensional subgroups and refinements of these is a crucial task. For nominal attributes, this is relatively straightforward, as we can consider individual attribute values as binary features. For numerical attributes, the task is more challenging as individual numeric values are not reliable statistics. Instead, we can consider combinations of adjacent values, i.e. bins. Existing binning strategies, however, are not tailored for subgroup discovery. That is, they do not directly optimize for the quality of subgroups, therewith potentially degrading the mining result. To address this issue, we propose FLEXI. In short, with FLEXI we propose to use optimal binning to find high quality binary features for both numeric and ordinal attributes. We instantiate FLEXI with various quality measures and show how to achieve efficiency accordingly. Experiments on both synthetic and real-world data sets show that FLEXI outperforms state of the art with up to 25 times improvement in subgroup quality.