Balancing provenance and accuracy tradeoffs in data modeling

A computer system for generating an analytics model, comprising:

• a computer having a processor and a computer-readable storage device;
• a program embodied on the storage device for execution by the processor, the program having a plurality of program modules, the program modules including:
• a receiving module configured to receive a data set having a defined first set of features;
• a defining module configured to define a second set of features based on an application of a set of domain knowledge data to the first set of features;
• a first generating module configured to generate a features hierarchy based on relationships between features of the first and second sets of features;
• and
• a second generating module configured to generate an analytics model based on a selection of features from the features hierarchy, wherein the analytics model includes a highest number of features of the second set of features while maintaining a defined accuracy value.

A computer program product for generating an analytics model, comprising a tangible storage device having program code embodied therewith, the program code executable by a processor of a computer to perform a method comprising:

• receiving a data set by the processor, the data set having a defined first set of features;
• defining a second set of features, by the processor, based on an application of a set of domain knowledge data to the first set of features;
• generating a features hierarchy, by the processor, based on relationships between features of the first and second sets of features;
• and
• generating an analytics model, by the processor, based on a selection of features from the features hierarchy, wherein the analytics model includes a highest number of features of the second set of features while maintaining a defined accuracy value.