Software development prioritization using trained model

A software development method, comprising:

• determining data associated with a first model feature of a trained machine learning (ML) model;
• determining a first feature summary of the first model feature based on the determined data;
• determining a set of similarities based on the first feature summary, the set of similarities comprising:
• a first similarity between a first software development item and the first model feature, and
• a second similarity between a second software development item and the first model feature,
• prioritizing the first software development item based on the set of similarities;
• and
• performing a software development task corresponding to the first software development item prior to a second software development task corresponding to the second software development item.

A computer readable storage medium encoded with program instructions structured to cause a processor to perform a method for prioritizing software development, the method comprising:

• determining data associated with a first model feature of a trained machine learning (ML) model;
• determining a first feature summary of the first model feature based on the determined data;
• determining a set of similarities based on the first feature summary, the set of similarities comprising:
• a first similarity between a first software development item and the first model feature, and
• a second similarity between a second software development item and the first model feature,
• prioritizing the first software development item based on the set of similarities;
• and
• performing a software development task corresponding to the first software development item prior to a second software development task corresponding to the second software development item.