The Delicacy of Accuracy: A Deep Dive on Classification Performance

The accuracy of Machine Learning models gives rise to one of the most confusing discussions in the world of Machine Learning. There are multiple reasons for that. First, many different performance metrics are used, which makes fair comparisons and transparent discussions hard. Secondly, expectations are often unrealistically high, caused by extremely overblown media coverage of ...

An introduction to the data manager

Working with Einstein Analytics I often hear people finding the data manager the most challenging part to learn. Perhaps because when people work with dashboards in core Salesforce we don’t have to shape our data the same way, we simply need to understand what objects we want to use in our report or dashboard. There ...

Welcome to the new data platform

Something new is coming to Einstein Analytics. Something you should pay attention to as it will change the way that you work with data. The most visible part of this new data platform is a new Data Prep editor. It’s more approachable and powerful featuring machine learning capabilities. Hints have been dropped at Dreamforce and ...

The ultimate bindings dashboard

A little more than a year ago I sat out to demystify bindings (or interactions as they are being called from Spring 20). I wrote a blog series covering data selection, data serialization, and data manipulation functions. It turned out to be quite a few blogs and quite a few bindings as well. I figured ...

Preparing Your Data For Einstein Discovery

Einstein Discovery is AI-powered analytics that enables business users to automatically discover relevant patterns based on their data – without having to build sophisticated data models. However, Einstein Discovery is only as good as the historical data it is analyzing. Wrangling the data, which is always the hardest part, involves cleaning and consolidating your historical ...