For contractual business, you should be able to capture ‘churned” customers, that is your training data should have a “churn” column. The problem will become binary classification problem, such as Logistic regression in Python, or Predict customer churn with R, or Predict employee turn over with Python.
Changing the world, one post at a time. Sr Data Scientist, Toronto Canada. https://www.linkedin.com/in/susanli/