The MB Inspect tool takes as input a rules or itemsets output of the MB Rules tool, and provides a listing and analysis of those rules that can be filtered on several criteria in order to reduce the number or returned rules or itemsets to a manageable number.
This tool uses the R programming language. Go to Options > Download Predictive Tools to install R and the packages used by the R Tool.
Minimum support level: Support is the proportion of transactions that contain the items in the itemset or association rule. This option sets the minimum required support level to be included in an inspection. The lower this value, the more rules or itemsets that will meet the criteria, but they will represent increasingly more uncommon combinations of items. A value of zero "turns-off" this filter.
Maximum support level: This option sets the upper bound of support for rules or itemsets that will be inspected. One reason to set an upper bound is that high levels of support may represent obvious and uninteresting rules or items sets that are frequently purchased (e.g., milk and bread in a supermarket). A value of zero "turns-off" this filter.
Minimum confidence level for association rules: Confidence is the proportion of transactions where the RHS (right-hand side) item(s) of an association rule are in the transactions that also contain the LHS (left-hand side) item(s) of that rule. In other words, it is a measure of the probability that the RHS item(s) will be in the transaction when the LHS item(s) are also in the transaction. This option sets the minimum required confidence level to be included in an inspection. The lower this value, the more rules or itemsets that will meet the criteria, but they will represent rules where the proportion of times the LHS item(s) occur in transactions that contain the RHS item(s). A value of zero "turns-off" this filter, which is only applicable for association rules.
Maximum confidence level for association rules: This option sets the upper bound of confidence for rules or itemsets that will be inspected. One reason to set an upper bound is that high levels of confidence may represent obvious and uninteresting rules or items sets (e.g., hot dogs and hot dog buns in a supermarket). A value of zero "turns-off" this filter, which is only applicable for association rules.
Minimum lift level for assoc. rules: Lift is the proportion of transactions that contain the RHS and LHS items relative to the proportion of time we would expect this to occur if the items were independent (unrelated) to one another. If the lift measure is one, then the RHS and LHS item(s) as often in transaction as they are expected to when the items have no relationship to one another. If the measure is less than one, then they occur less frequently together than would be expected if they were unrelated to one another (they "repulse" one another). If the measure is greater than one, then the LHS and RHS item(s) occur together more often then is expected by random chance. In general, we are interested in association rules that have a lift substantially greater then one. However, as this minimum lift criteria increases, we have fewer returned rules. A value of zero "turns-off" this filter, which is only applicable for association rules.
Maximum lift level for assoc. rules: This option set the upper bound of lift for rules or itemsets that will be inspected. One reason to set an upper bound is that high levels of lift may represent obvious and uninteresting rules or items sets (e.g., hot dogs and hot dog buns in a supermarket). A value of zero "turns-off" this filter, which is only applicable for association rules.
Sort association rules by: This option causes the returned association rules to be sorted by the user's choice of support, confidence, or lift values, which can assist in interpreting the rules.
Graphics Options
Plot size: Select inches or centimeters for the size of the graph.
Graph resolution: Select the resolution of the graph in dots per inch: 1x (96 dpi); 2x (192 dpi); or 3x (288 dpi). Lower resolution creates a smaller file and is best for viewing on a monitor. Higher resolution creates a larger file with better print quality.
Base font size (points): Select the size of the font in the graph.
Output
The Output ("O") connection returns a data stream that contains the association rules or itemsets. In the case of association rules, the fields include LHS (a comma separated list of left-hand side item(s) in each rule), RHS (a comma-separated list of right-hand side item(s) in each rule), Support (the level of support for each rule), Confidence (the level of confidence for each rule), and Lift (the level of lift each rule possesses). In the case of itemsets, the fields include Items (a comma separated list of items in each itemset) and Support.
The Report ("R") connection returns a set of report snippets, that include a summary of the filters rules to develop the inspection report, the rules or itemsets generated (the same information as returned in via the Output connection), and one (for itemsets) or two (for association rules) diagnostic plots to aid the user in understanding the relationships between different items and rules.
MB Inspect Tool