Evolved machine learning models

A system, comprising:

• a processor configured to:
• determine a plurality of initial machine learning models based on a plurality of original features;
• filter the plurality of initial machine learning models based at least in part on corresponding validation scores associated with the plurality of initial machine learning models, wherein to filter the plurality of initial machine learning models, the processor is further configured to select a subset of the initial machine learning models as one or more surviving machine learning models;
• generate one or more evolved machine learning models, wherein at least one of the evolved machine learning models is based at least in part one or more new features, wherein the one or more new features are based at least in part on a transformation of at least one feature of the one or more surviving machine learning models;
• compare corresponding validation scores associated with the plurality of evolved machine learning models and the surviving machine learning models;
• and
• selecting based on the comparison of the corresponding validation scores, at least one of the one or more evolved machine learning models or the one or more surviving machine learning models as one or more new selected surviving machine learning models;
• and
• a memory coupled to the processor and configured to provide the processor with instructions.

A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

• determining a plurality of initial machine learning models based on a plurality of original features;
• filtering the plurality of initial machine learning models based at least in part on corresponding validation scores associated with the plurality of initial machine learning models, wherein filtering the plurality of initial machine learning models includes selecting a subset of the initial machine learning models as one or more surviving machine learning models;
• generating one or more evolved machine learning models, wherein an at least one of the evolved machine learning models is based at least in part one or more new features, wherein the one or more new features are based at least in part on a transformation of at least one feature of the one or more surviving machine learning models;
• comparing corresponding validation scores associated with the plurality of evolved machine learning models with the corresponding validation scores associated with the surviving machine learning models;
• and
• selecting based on the comparison of the corresponding validation scores, at least one of the one or more evolved machine learning models or the one or more surviving machine learning models as one or more new selected surviving machine learning models.