Systems and methods for calculating a synthetic data error factor to simulate missing network element data

A non-transitory computer-readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining steps of:

• identifying a first set of network elements with less than a first specified percentage of missing data;
• for each network element in the first set of network elements, randomly removing a second percentage of data associated with each network element in the first set of network elements, to generate a test data set;
• applying a plurality of data fill methods to the test data set to generate a filled data set for each data fill method;
• calculating, for each data fill method, a percentage of missing data successfully filled and an error between the filled data set and the removed second percentage of data;
• analyzing relationships between the removed second percentage of data, the calculated percentage of missing data successfully filled, and the error for each data fill method to generate an error curve for each data fill method;
• and
• selecting, based on corresponding error curves, one or more data fill methods to apply to missing data in a network element.

A device comprising:

• a processor configured to
• identify a first set of network elements with less than a first specified percentage of missing data;
• remove a second percentage of data associated with each network element in the first set of network elements, to generate a test data set for each network element in the first set of network elements;
• apply a plurality of data fill methods to the test data set to generate a filled data set for each data fill method;
• calculate a percentage of missing data successfully filled and an error between the filled data set and the removed second percentage of data for each data fill method;
• analyze relationships between the removed second percentage of data, the calculated percentage of missing data successfully filled, and the error for each data fill method to generate an error curve for each data fill method;
• and
• select one or more data fill methods to apply to missing data in a network element based on corresponding error curves.