| CPC G06F 11/3636 (2013.01) | 20 Claims |
|
1. A system comprising:
persistent storage containing a plurality of representations of a plurality of software defects identified in a software product; and
one or more processors configured to perform operations comprising:
determining, for each respective software defect of the plurality of software defects, corresponding one or more attribute values that represent a software development history associated with the respective software defect;
determining, for each respective software defect of the plurality of software defects, using a machine learning model, and based on the corresponding one or more attribute values, a corresponding escalation value representing a likelihood of the respective software defect being escalated for resolution after release of the software product, wherein the machine learning model has been trained using corresponding software development histories of a plurality of training software defects that were escalated for resolution after release of one or more prior versions of the software product;
based on the corresponding escalation value of each respective software defect, selecting, for resolution prior to the release of the software product, a defect subset comprising one or more software defects of the plurality of software defects;
storing a representation of the defect subset in the persistent storage; and
resolving, prior to release of the software product, at least one software defect of the one or more software defects of the defect subset.
|