Microsoft Azure Machine Learning Studio Review

Split dataset, data visualization are helpful, but it needs integrated Pivot Table feature

What is our primary use case?

My  primary use of ML Studio is to experiment with different algorithms and learn the techniques of machine learning. In the meantime, I have developed a few models related to finance. One of the predictive models I designed was an Invoice Discrepancy Prediction model using a Multiclass Neural Network algorithm. This model predicts if an invoice will have a variance of some sort when checked against the purchase order, before the payments are to be processed.

How has it helped my organization?

Thanks to the model I designed, the productivity of processing invoices has increased by over 11%, because the team members only verify invoices that are discrepancy-free now.

What is most valuable?

  • Split dataset
  • variety of algorithms
  • visualizing the data
  • drag and drop capability 

are the features I appreciate most. 

The capability to model the data by finding empty cells and filling missing values by deriving the median and more, are great features that makes the job way easier.

What needs improvement?

I personally would prefer if data could be tunneled to my model through a SAP ERP system. It also needs features of Excel, such as Pivot Tables, integrated.

For how long have I used the solution?

Less than one year.
Disclosure: I am a real user, and this review is based on my own experience and opinions.
Add a Comment
Sign Up with Email