User interface for assessment of classification model quality and selection of classification model cut-off score

A computer-implemented method comprising:

• receiving received data regarding results of exposing a sample population to a sample stimulus;
• generating, based on the received data, a classification model providing prediction data indicating predicted users in a target population who will respond to a target stimulus according to a predefined user response category;
• displaying in a graphical user interface (GUI):
• a graphical representation of the generated classification model,
• wherein the graphical representation plots, according to the generated classification model, the prediction data as a function of a variable number of users eligible to receive the target stimulus;
• and
• wherein a cut-off in the graphical representation graphically separates the variable number of users of the classification model into two regions, a first region that corresponds to target data for a target group to receive the target stimulus and a second region that corresponds to exclusion data for an excluded group to not receive the target stimulus;
• and
• a plurality of options each specifying one of different objectives for determining a proportion of users in the target population to expose to the target stimulus, wherein the plurality of options control a location of the cut-off in the graphical representation and comprise a first option that indicates that the location of the cut-off accounts for a first factor for increasing a number of targeted users who will respond to the target stimulus according to a predefined user response category and a second factor related to a detriment of a user of the GUI from employing the target stimulus, the first factor different from the second factor;
• receiving data input from the user of the GUI selecting a selected option of the plurality of options;
• determining the location of the cut-off in the graphical representation of the generated classification model based on the selected option;
• predicting proportion data indicating the proportion of users in the target population to expose to the target stimulus based on the determined location of the cut-off;
• determining one of predefined quality categories for the classification model;
• and
• responsive to the received data input and the determined one of the predefined quality categories, issuing one or more indications as to whether to use the classification model as a basis for exposing the proportion of users in the target population to the target stimulus according to the proportion data.

A computing device comprising processor and memory, the memory containing instructions executable by the processor wherein the computing device is configured to:

• receive received data regarding results of exposing a sample population to a sample stimulus;
• generate, based on the received data, a classification model providing prediction data indicating predicted users in a target population who will respond to a target stimulus according to a predefined user response category;
• display in a graphical user interface (GUI):
• a graphical representation of the generated classification model,
• wherein the graphical representation plots, according to the generated classification model, the prediction data as a function of a variable number of users eligible to receive the target stimulus;
• and
• wherein a cut-off in the graphical representation graphically separates the variable number of users of the classification model into two regions, a first region that comprises target data for a target group to receive the target stimulus and a second region that comprises exclusion data for an excluded group to not receive the target stimulus;
• and
• a plurality of options each specifying one of different objectives for determining a proportion of users in the target population to expose to the target stimulus, wherein the plurality of options control a location of the cut-off in the graphical representation and comprise a first option that indicates that the location of the cut-off accounts for a first factor for increasing a number of targeted users who will respond to the target stimulus according to a predefined user response category and a second factor related to a detriment of a user of the GUI from employing the target stimulus, the first factor different from the second factor;
• receive data input from the user of the GUI selecting a selected option of the plurality of options;
• determine the location of the cut-off in the graphical representation of the generated classification model based on the selected option;
• predict proportion data indicating the proportion of users in the target population to expose to the target stimulus based on the determined location of the cut-off;
• determine one of predefined quality categories for the classification model;
• and
• responsive to the received data input and the determined one of the predefined quality categories, issue one or more indications as to whether to use the classification model as a basis for exposing the proportion of users in the target population to the target stimulus according to the proportion data.