Please enable JavaScript.
Coggle requires JavaScript to display documents.
Ch 21 - 23 (Set Up Prediction System (Choose deployment strategy…
Ch 21 - 23
Set Up Prediction System
Retrain the model
Pay attention to time periods and how they can influence the model
Pay attention to the model environment and subtle changes that could occur
Choose deployment strategy
Drag-and-drop
What we used for project one, going to a model and clicking predict then dragging and dropping a new file with all the same features in
Application Programming Interface (API)
relatively straight-forward for those able to program in R or Python. An Application Programming Interface (API) is created on the DataRobot server, allowing a developer to write a program that uploads new patient data to the API, which then returns a probability that the patient will be readmitted.
DataRobot Prime
creates an approximation of the selected model, available as code in the Python and Java programming languages
The disadvantage of this approach is that it is now an in-house responsibility to integrate and maintain the model code.
The advantage, on the other hand, is that it provides vendor independence and allows the use of an organization’s own servers for processing of new cases.
Batch
uses the DataRobot API to upload and score multiple large files in parallel.
In-place with Spark
allows for exporting the selected model as an executable file to be used in an Apache Spark environment. Spark is a fast and widely distributed data processing environment.
Document Modeling Process for Reproducibility
Model Documentation
Work under the assumption that the project will need to be revisited within a year, and think through what information would be helpful to have immediate access to at that time. Implement the system and write documentation that provides all relevant information for future project stakeholders.
Where did the data come from? How was the data processed? What parameters or selections were used when creating and selecting the model? How is the model used within the business?
Create Model Monitoring and Maintenance Plan
Potential Problems
This serves to informs others what to do in the event of changes in the environment that stand to impact the effectiveness of the model. This chapter is about detecting when the model performance has deteriorated such that the model must be retrained.