Azure Machine Learning is part of the Cortana Intelligence Suite. It’s a cloud based collaborative drag and drop tool that can be used to build, test, and deploy predictive analytics solutions. We recently worked with Casella Waste Systems to analyze their customer and sales data using Azure ML. We found Azure ML to be a useful tool that allowed us to visualize our work and avoid coding when it wasn’t necessary. However, the process of creating successful experiments didn’t come without some speed bumps. Here are some things that we discovered along our ML journey, delivered in the spirit of a Buzzfeed article.
1. Your experiment starts out nice and simple
2. And ends up looking like this
3. You have multiple people working on an experiment
4. But you see this when everyone tries to edit the experiment at the same time
All that lost work T.T
5. You start seeing this in your sleep
6. And this in your nightmares
7. You think you set up your experiment correctly, but you get this as a result
8. Or this
9. Or this
This isn’t school, seeing 100% is bad
10. You forget to check on your experiment and come back to find that it erred 2 hours ago
11. You let your experiment run for a while thinking you’ll get better results, only to see this
12. You wish the error message you’re getting was a little more detailed
13. Then immediately regret that wish
14. You want to use the Text Analytics API, but the tier you want is out of your project’s budget
And your project’s budget is $0, after all it’s a PoC
15. So you make your own text analytics experiment in Azure ML
16. And it actually turns out pretty good!
CLICK HERE to learn more about Microsoft Azure and how Tallan can help you migrate to the cloud today!
_________________________________________________________________________________________
Authored By:
Lu Li & Iu-Wei Sze