PaaS Partner Community

Machine Learning in Digital Process Automation — Part III by Ralf Mueller

Juergen Kress
PaaS Partner Adoption


A lot has happened since the publishing of Part II of this article series. Autonomous Data Warehouse (ADW) has advanced and on the process side we’re working on a truly multi-tenant, OCI native offering. As part of this, we’re re-architecting parts of the Machine Learning capabilities for Digital Process Automation and we will talk about this in a later article. In this article though, we’d like to demonstrate how ADW and Oracle REST Data Services can be used today for the consumption of Machine Learning models in Business Processes or any other component that supports RESTful Services.

Use Case

For this article we’re considering a Rental Car Use Case. We pick this use case for various reasons:

· Renting a car is well understood by many people, almost all of us went through some great or miserable experience while renting a car.

· We have a great formal description of the case in the form of EU Rent, which was originally developed as a challenge for Business Rules implementations.

· Quite incidentally, there are two public data sets available that we could use for Machine Learning
- A Car Evaluation data set for the prediction of the car safety. This can be used to build classification models for the prediction of the safety of a car.
- A Car Mileage per Gallon (MPG) data set for the prediction of the mileage per gallon of a car. This data set can be used to build regression models. Reda the complete article here. Read the complete article here.

PaaS Partner Community

For regular information on Oracle PaaS become a member in the PaaS (Integration & Process) Partner Community please register here.

clip_image003 Blog clip_image005 Twitter clip_image004 LinkedIn image[7][2][2][2] Facebook clip_image002[8][4][2][2][2] Wiki

Technorati Tags: SOA Community,Oracle SOA,Oracle BPM,OPN,Jürgen Kress

Be the first to comment

Comments ( 0 )
Please enter your name.Please provide a valid email address.Please enter a comment.CAPTCHA challenge response provided was incorrect. Please try again.