📄️ 4ft-Miner Results
The 4ft-Miner is the core GUHA procedure for mining enhanced association rules of the form Antecedent → Succedent. It discovers rules supported by a wide range of statistical quantifiers, including confidence and support.
📄️ SD4ft-Miner Results
The SD4ft-Miner is the subgroup discovery variant of the 4ft-Miner. It mines couples of rules — comparing how the same pattern behaves across two different subgroups of the data. This makes it particularly useful for identifying whether a relationship holds differently for distinct segments.
📄️ CF-Miner Results
The CF-Miner (Category Fishery Miner) discovers rules that describe how the distribution of a target categorical attribute shifts under specific antecedent conditions. It is particularly useful for finding circumstances that boost or suppress the occurrence of a particular category within a target attribute.
📄️ UIC-Miner Results
The UIC-Miner (Uplift in Categories Miner) is designed to find conditions under which rare categories in a target attribute are proportionally boosted. It is especially valuable for imbalanced datasets where a minority category — such as a rare outcome or a high-value event — is difficult to isolate with standard association rule mining.