Preliminaries

Magnum Opus analyses data to detect rules and itemsets within those data.

The data is imported from a text file in one of several supported formats (see transaction data and attribute-value data).   Users typically extract data from a database into a text file in a suitable format.  The data import process supports considerable flexibility in the formats that may be employed.

Once the data is imported into Magnum Opus, the user selects settings to control a search for rules and itemsets in the data.  The user can choose between five measures of the importance of a rule, leverage, lift, strength, coverage, or support (see search modes).  Two measures, leverage and coverage, are available for itemsets.  The user also specifies the maximum number of rules or itemsets to be found, and can place restrictions on those to be considered.

A search is then conducted.  Within the restrictions specified by the user, Magnum Opus finds the rules or itemsets with the highest values on the specified measure.  Magnum Opus will only find fewer than the specified number of rules or itemsets if the search is terminated by the user or there are fewer than the specified number that satisfy the user specified constraints.

The rules and itemsets found are recorded in an output file and may optionally be exported to a comma separated value file suitable for input into a spreadsheet for further analysis.