Generating synthetic data using reject inference processes for modifying lead scoring models

A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computer system to:

• identify an original dataset corresponding to an output of a lead scoring model that generates scores for a plurality of prospects, the scores indicating a likelihood of success of prospects of the plurality of prospects;
• generate, based on the original dataset, an imputed dataset using a reject inference model on a subset of the plurality of prospects to generate synthetic outcome data for the subset;
• and
• update the lead scoring model using the imputed dataset by modifying at least one parameter of the lead scoring model based on the synthetic outcome data.

In a digital medium environment for classifying lead prospects, a system for using reject inference to generate synthetic data for modify lead scoring models comprising:

• at least one processor;
• and
• a non-transitory computer memory comprising:
• an original dataset comprising data for a plurality of prospects;
• and
• instructions that, when executed by the at least one processor, cause the system to:
• identify an output of a lead scoring model that generates scores for a plurality of prospects, the scores indicating a likelihood of success of each prospect of the plurality of prospects;
• select a reject inference model from a plurality of reject inference models based on a plurality of simulations performed on historical prospect data associated with the original dataset using the plurality of reject inference models;
• generate an imputed dataset using the selected reject inference model on a subset of the plurality of prospects corresponding to rejected prospects to generate synthetic outcome data representing simulated outcomes of the subset of the plurality of prospects;
• and
• modify the lead scoring model based on the synthetic outcome data of the imputed dataset by modifying at least one parameter of the lead scoring model.