Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Does another condition really add information?

Suppose plan=monthly AND channel=web has a high cancellation rate, but plan=monthly already has the same rate. Is the extra condition informative? Generalization-aware quality compares a description with all descriptions obtained by removing conditions, including the empty description Lemmerich, 2014.

A transparent redundancy example

Loading...

Both monthly descriptions have target share 6/8=3/46/8=3/4 or 3/43/4, respectively. The more specific one is enriched relative to the full dataset but adds no rate improvement over the monthly parent. Its generalization-aware rate score is zero. A useful table can therefore distinguish “associated with the target” from “adds an improvement over simpler explanations.”

Two forms of generalization awareness

For a subgroup GG, let H≺GH\prec G denote descriptions obtained by removing at least one condition. The empty description is included.

The generic wrapper subtracts the best quality of a generalization:

qGA(G)=q(G)−max⁡H≺Gq(H).q_{GA}(G)=q(G)-\max_{H\prec G}q(H).

The binary statistic-based measure instead subtracts the best target share inside its size weighting:

ra(G)=(nG/N)a(pG−max⁡H≺GpH).r_a(G)=(n_G/N)^a\left(p_G-\max_{H\prec G}p_H\right).

These are different measures. Likewise, the numeric version compares subgroup mean with the largest generalization mean and uses nGan_G^a. The specialized binary and numeric measures search increases; there is no direction argument.

Generalizations here only remove conditions. Replacing age>40 with age>30 does not count as a generalization for this API, even if it covers more rows. Thus the score depends on the description, not just the covered rows.

Use a search that supplies the reference

Loading...

GeneralizationAwareApriori propagates references level by level. GeneralizationAwareDFS visits the tree in reverse sibling order so that the necessary generalizations are processed first. Standard DFS and other ordinary searches do not provide these references and reject these measures.

For one manually specified description, the helper enumerates its generalizations:

Largest generalization share: 0.75
Child score: 0.0

There are 2d−12^d-1 proper generalizations for a description with dd conditions. The searches maintain references incrementally rather than independently enumerating every subset for every evaluated candidate.

Generalization awareness, diversity, and validation

These address separate questions:

For classifier auditing, GeneralizationAwareQF(ROCAUCQF(...)) subtracts the best generalization’s weighted quality. When testing such results with the significance helpers, the tested statistic is the underlying qf.value, not the search-dependent generalization-aware subtraction.

The searches offer difference_based="auto", "on", or "off". The auto setting uses difference-based bounds with negated conditions or overlapping numeric intervals. This is an optimization choice; it should not redefine the measure or change the attainable quality values.

Experiment. Change only the outcomes for monthly web customers. At what point does the two-condition description gain a positive generalization-aware score? Remember to compare it with both one-condition generalizations.

References
  1. Lemmerich, F. (2014). Novel Techniques for Efficient and Effective Subgroup Discovery [Phdthesis]. University of Würzburg.