A Predictive Insights model is a model which was trained by the Predictive Insights machine-learning engine. The process in which a machine learning algorithm uses account information to detect patterns and relationships between attributes and customer or prospect accounts in a dataset to generate predictions for prospective accounts.
Model training is a process in which the Predictive Insights machine learning algorithm learns from a dataset by identifying patterns and relationships between the attributes and the customer/prospect label to generate predictions (scores) for new accounts. Once a model has been trained, any account dataset can be scored against it for account prioritization.