Audience comparison

A computer program product for providing a user interface representing differences between segments of end users, said computer program product comprising:

• a non-transitory computer-readable storage medium comprising program instructions executable by a computer, the program instructions comprising:
• first instructions to receive user input on the user interface indicating a selection of a first segment and a second segment from the segments, wherein the first segment comprises a subset of the end users and the second segment comprises another subset of the end users;
• second instructions to randomly assign the end users into either a first category or a second category, wherein the randomly assigning comprises assigning each of the end users an identifier (ID) randomly, placing each of the end users having the ID that is odd into the first category, and placing each of the end users having the ID that is even into the second category;
• third instructions to select non-overlapping subsets of the end users from the first segment and the second segment by selecting a first subset of the first segment of the end users in the first category and selecting a second subset of the second segment of the end users in the second category;
• fourth instructions to identify metrics and dimensions for the first segment and for the second segment;
• fifth instructions to identify common metrics between the first segment and the second segment from the metrics, and identify common dimensions between the first segment and the second segment from the dimensions;
• sixth instructions to identify common metrics between the first subset of the first segment and the second subset of the second segment;
• seventh instructions to identify common dimensions between the first subset of the first segment and the second subset of the second segment;
• eighth instructions to compare the common metrics and the common dimensions to identify a subset of the common metrics and a subset of the common dimensions with a largest relative statistical difference using a three sample statistical test, wherein:
• the compare includes identifying the largest relative statistical difference in the common metrics and the largest relative statistical difference in the common dimensions for the first segment and the second segment by comparing respective distributions of the common metrics and the common dimensions for the first subset and the second subset using the three sample statistical test, and
• the three sample statistical test includes forming a null-hypothesis, calculating a 3-sample test statistic, and computing a p-value from the 3-sample test statistic;
• and
• ninth instructions to represent, on the user interface, the identified subset of the common metrics between the first segment and the second segment having the largest relative statistical differences and the identified subset of the common dimensions between the first segment and the second segment having the largest relative statistical differences.

A system for providing a user interface representing differences between segments of end users, the system comprising:

• at least one memory including instructions;
• and
• at least one processor that is operably coupled to the at least one memory and that is arranged and configured to execute the instructions that, when executed, cause the at least one processor to:
• receive user input on the user interface indicating a selection of a first segment and a second segment, wherein the first segment comprises a subset of end users and the second segment comprises another subset of the end users;
• randomly assign the end users into either a first category or a second category;
• select non-overlapping subsets of the end users from the first segment and the second segment by selecting a first subset of the first segment of the end users in the first category and selecting a second subset of the second segment of the end users in the second category;
• identify metrics and dimensions for the first segment and for the second segment;
• identify common metrics between the first segment and the second segment from the metrics, and identify common dimensions between the first segment and the second segment from the dimensions;
• identify common metrics between the first subset of the first segment and the second subset of the second segment;
• identify common dimensions between the first subset of the first segment and the second subset of the second segment;
• compare the common metrics and the common dimensions to identify a subset of the common metrics and a subset of the common dimensions with a largest relative statistical difference using a two sample statistical test, wherein:
• the compare includes identifying the largest relative statistical difference in the common metrics and the largest relative statistical difference in the common dimensions for the first segment and the second segment by comparing respective distributions of the common metrics and the common dimensions for the first subset and the second subset using the two sample statistical test, and
• the two sample statistical test includes forming a null-hypothesis, calculating a 2-sample test statistic, and computing a p-value from the 2-sample test statistic;
• determining an order of the identified subset of the common metrics and the identified subset of the common dimensions such that those having a smaller p-value appear higher in the order;
• and
• represent, on the user interface, the identified subset of the common metrics between the first segment and the second segment having the largest relative statistical differences and the identified subset of the common dimensions between the first segment and the second segment having the largest relative statistical differences according to the determined order.