I’m one of those people who can’t resist peeking behind the scenes, and so when the Key Influencers visual appeared in Power BI I couldn’t help wondering how it worked its machine learning magic. Using DAX Studio to look at the DAX queries generated by the visual proved to be very revealing: it turns out that it uses a number of new DAX functions that are undocumented and probably not meant to be used outside Microsoft.
Machine Learning is all about data… and algorithms. But first and most importantly it’s about data. And it’s not just any data, we need enough, high quality and (and in many cases) “cleaned” data. When we talk about cleaning data, we normally use the word ‘wrangling’. Wrangling is like washing clothes: your dirty data goes in and clean, neatly ironed and folded data comes out.
In the previous post we looked at enabling the built-in integration of Dynamics NAV and Time Series, which uses a Machine Learning (ML) model to predict inventory or cash requirements. This time we will make a very basic example with the sole aim of sending data from Dynamics NAV as input into an ML model that is running as a web service, and receive a result back from the model.
This post is a summary of what was new already in Dynamics NAV 2017: Using “Microsoft Azure Machine Learning Studio” to create (load) and then publish a model which we will call from Dynamics NAV to make inventory or cash forecasts. This is the model which is already available:
Machine Learning (ML) is a branch of Artificial Intelligence (AI) that enables software to do more on its own, such as make predictions and offer suggestions, by analyzing and learning from the data it already has. In short, ML helps make software more proactive in the way it supports your business decisions.