Take your ED model from Good to Great

Einstein Discovery accelerates the embedding of augmented analytics in a business user’s work environment. The predictive models are created by the platform using a “No Code AI Approach”, which means that the algorithms to train these models are part of the solution, and don’t need to be coded by advanced developers or data scientists. To ...

Einstein Discovery: How good is my model really?

As artificial intelligence, and specifically machine learning, is conquering today’s business world, a new way of human machine interaction enters our professional lives. We are more and more guided by predictive models that prioritise our work and give recommendations to improve our business. Once widely adopted, this embedding of so-called augmented analytics can bring tremendous ...

Einstein Analytics: A robust approach for performing period over period analysis (using a single date picker)

Einstein Analytics dashboard pattern for dynamic Period over Period Analysis using a single date picker. Highlights: * Works with a single standard date widget * Works with absolute dates * Works with relative date bonus Allows switching between \"current period vs. prior period\" (example: Jan-Feb 2019 vs. Nov-Dec 2018) & \"current period vs same period prior year\" (example: Jan-Feb 2019 vs. Jan-Feb 2018)

SAQL simply explained – Part 2

In the first part of this blog series, I explained what is SAQL and the anatomy of SAQL. This will be the foundation for the rest of this series. The SAQL query we covered was simply, in fact, there was no reason to write that query in SAQL, which I also mentioned isn’t recommended for ...

SAQL simply explained – Part 1

When we create dashboards in Einstein Analytics most of us rely on the UI. In the dashboard editor, we click “New Step” select our dataset, define the measure and a grouping whereafter we add it to the dashboard. In other words, with point and click, we can create a great dashboard that gives insight into the data. ...

A Combo-Chart Hack

Sometimes you have a really great idea for a chart. You know exactly what you want, you have the calculations ready only to realize that the specific chart in mind does not 100% support what you want to do. It’s a typical use case that pops up on a regular basis. A few weeks ago ...