Automatic segmentation of data derived from learned features of a predictive statistical model

A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a processor of a data processing system, causes the data processing system to implement a statistical model tool for providing insight into decision making, wherein the computer readable program causes the data processing system to:

• apply, by the statistical model tool, the statistical model to an input image to generate an original classification probability;
• iteratively modify, by an image modification component executing within the statistical model tool, each portion of the input image to generate a modified image;
• apply, by the statistical model tool, the statistical model to the modified image to generate a new classification probability for each portion of the input image;
• and compare, by a compare component executing in the statistical model tool, each new classification probability to the original classification probability to generate a respective probability distance;
• and
• generate, by a distance map generator executing within the statistical model tool, a distance map data structure based on the probability distances, wherein the distance map data structure represents an impact each portion of the input image has on determining classification probability by the statistical model.

An apparatus comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a statistical model tool for providing insight into decision making, wherein the instructions cause the processor to:
• apply, by the statistical model tool, the statistical model to an input image to generate an original classification probability;
• iteratively modify, by an image modification component executing within the statistical model tool, each portion of the input image to generate a modified image;
• apply, by the statistical model tool, the statistical model to the modified image to generate a new classification probability for each portion of the input image;
• and compare, by a compare component executing in the statistical model tool, each new classification probability to the original classification probability to generate a respective probability distance;
• and
• generate, by a distance map generator executing within the statistical model tool, a distance map data structure based on the probability distances, wherein the distance map data structure represents an impact each portion of the input image has on determining classification probability by the statistical model.