Interactive Machine Learning (IML) is to include a human in the machine learning loop, observing the result of learning and providing input meant to improve the learning outcome.
Cohort discovering is an unsupervised machine learning process to discove the distribution of persons (e.g. patients, and customers) with selected features. However, it will be improved by adding meaningful input from person to align the learning model with targeting policy/business objective.
We develop this tool to involve the policy/business expert into the machine learning loop so that the learning outcome is algined with policy/business objective.