Final Thoughts on Delivering the Predictive Model to the Client

We have now completed modeling activities and also created a financial analysis to indicate to the client how they can use the model. While we have created the essential intellectual contributions that are the data scientists' responsibility, it is necessary to agree with the client on the form in which all these contributions will be delivered.

A key contribution is the predictive capability embodied in the trained model. Assuming the client has the capability to work with the trained model object we created in scikit-learn, this model could be saved to disk and sent to the client. Then, the client would be in a position to use it within their workflow. Alternatively, it may be necessary to express the model as a mathematical equation (i.e. logistic regression) or a set of if-then statements (i.e. decision tree or random forest) that the client could use to implement the predictive capability in SQL. While expressing random...