Artificial Intelligence Based Process Routing Using Amazon Machine Learning

As it might be evident from some of my previous blog posts, at AgilePoint, AI and Natural Language Processing have been at forefront of our product development in last few months. Things like skipping process instances or rolling them back based on certain key decision factors governing the state of that instance were always strong points for the product but with Machine Learning and Natural Language Processing we are trying to take it few notches up.

Previously we had done this with Microsoft Azure Machine Learning Studio and Salesforce Prediction Builder and got some great feedback from clients and today I am happy to announce that we have extended this capability to Amazon machine learning as well.

For those of you who are new to AWS Machine Learning (Amazon ML), it is
a robust, cloud-based service that makes it easy for developers of all skill levels to use machine learning
technology. Amazon ML provides visualization tools and wizards that guide you through the process of
creating machine learning (ML) models without having to learn complex ML algorithms and technology.
Once your models are ready, Amazon ML makes it easy to obtain predictions for your application
using simple APIs, without having to implement custom prediction generation code, or manage any
infrastructure. Infact compared to some of the other prediction builders I have tried, AWS machine learning seems to be easiest to setup with just clicks and no code.

In the following video, I am actually going to step by step build one of the prediction models for you to get familiar with how this is done.