Azure Machine Learning

News from PASS Summit’14 for Business Analytics Professionals: #sqlpass #summit14

Standard

This post is a quick summary for all Business Analytics related updates that I saw at PASS Summit’14:

1. Theme of the Keynote(s)/Session(s) seemed to be around educating the community about the benefits of the NEW(er) tools. I saw demos/material for cloud-based tools like SQL databases, Azure stream analytics, Azure DocumentDB, AzureHDInsight & Azure Machine learning. The core message was pretty clear: A data professional does two things – 1) Guards data OR 2) helps to generate Insights from Data – And they will need to keep up-to-date on the new tools to future-proof their career.

Read more about this here: http://blogs.technet.com/b/dataplatforminsider/archive/2014/11/05/microsoft-announces-major-update-to-azure-sql-database-adds-free-tier-to-azure-machine-learning.aspx

2. Coming soon: Power BI will be able to connect to on-premise SSAS data sources (multi-dim & tabular).

3. Coming soon: A better experience to create Power BI dashboards.

Read more about Power BI updates here: http://www.jenunderwood.com/2014/11/05/pass-summit-2014-bi-news/

4. Azure Machine Learning adds a free-tier! You won’t need a credit-card/subscription to sign up for this.

5. I also saw sessions proposing new way of thinking about an architecture for “Self Service BI” and “Big Data” which might be worth following because since these are newer tools, it’s definitely worth considering an architecture that’s designed to make the most of the investments in these new tools. That’s it & I’ll leave you with a quote from James Phillips from Day 1’s keynote:

Back to basics: Multi Class Classification vs Two class classification.

Standard

Classification algorithms are commonly used to build predictive models. Here’s what they do (simplified!):

Machine Learning Predictive Algorithms analytics Introduction

Now, here’s the difference between Multi Class and Two Class:

if your Test Data needs to be classified into two classes then you use a two-class classification model.

Examples:

1. Is it going to Rain today? YES or NO

2. Will the buyer renew his soon-to-expire subscription? YES or NO

3. What is the sentiment of this text? Positive OR Negative

As you can see from above examples the test data needs to be classified in two classes.

Now, look at example #3 – What is the sentiment of the text? What if you also want an additional class called “neutral” – so now there are three classes and we’ll need to use a multi-class classification model. So, If your test data needs to be classified into more than two classes then you use a multi-class classification model.

Examples:

1. Sentiment analysis of customer reviews? Positive, Negative, Neutral

2. What is the weather prediction for today? Sunny, Cloudy, Rainy, Snow

I hope the examples helped, so next time you have to choose between multi class and two class classification models, ask yourself – does the problem ask you to predict two classes or more? based on that, you’ll need to pick your model.

Example: Azure Machine Learning (AzureML) studio’s classifier list:

Azure Machine Learning classifiers list

I hope this helps!