Introducing Azure ML
WARNING!
This presentation is now obsolete. The information in this talk has not been updated in a while and could be outdated. Use the information in this presentation at your own risk and be sure to double-check things to ensure that any information you use is accurate.ABSTRACT
Azure Machine Learning is a point-and-click Software-as-a-Service offering on the Microsoft Azure platform. It allows data scientists to manage, cleanse, and filter data; train, score, and evaluate models; and write custom components in R and Python. Once the data scientist's work is done, Azure ML then automatically generates a production-ready web service to implement the model, saving significant development effort. This talk will walk through the Azure ML offerings and discuss how they may integrate into a mature business platform.ADDITIONAL MEDIA
No recordings or additional media are available for this talk.SLIDES
Click here to access the slides for this presentation.
The slides are licensed under Creative Commons Attribution-ShareAlike.
DEMO CODE
No demos are available for this presentation.LINKS & FURTHER INFO
Basic Links
- Azure ML Studio is the IDE for Azure Machine Learning. You will do most of your work there.
- The folks at Data Science Dojo put together a great series on using Azure ML, and I used their video series as the basis for my Titanic example. They also have several tutorials and demos using Azure ML.
- Jamie Dixon's example involving Wake County, North Carolina election data is interesting and worth perusing.
- I am indebted to David Crook for getting me interested in Azure ML. Here is a Channel 9 video David put together to forecast home prices. He also has several blog posts on the topic.
- My Titanic example focuses on decision forests. Wikipedia has a good article on random forests and Microsoft Research has gone further with the concept of decision jungles (which actually scores slightly better than my decision forest). I also like Edwin Chen's explanation of random forests in layman's terms.
Data Sets
- My SQL Saturday data set is available on the website.
- The Titanic data set is available as part of a Kaggle challenge. I used the "train" data set.