ARM
ARM is an acronym for Association Rule Mining. ARM is used for discovering interesting relations between variables in a dataset.
CONFIGURATION
OPTION | DESCRIPTION |
---|---|
Column Selector | The column selector allows the user to specify which columns have been selected for consideration for the ARM analysis. |
Confidence | Fraction of the number of transactions that contain X∪Y to the total number of records that contain X expressed as a range from 1% to 100% |
Frequency | The percentage of the dataset in which this association must occur expressed as a range from 0 to 100%. |
INPUT
Any data.
OUTPUT
On running the ARM analysis on our president/party/state dataset and filtering on the strongest and most frequent relations we see:
This indicates that:
- Republican presidents from Ohio comprise 13.6% of the dataset.
- Democratic-Republican presidents from Virgina comprise 6.8% of the dataset.