Since our launch in 2012, we've been on a mission: to make digital identification simple and secure for everyone, and everything. In that time, we've expanded constantly, and been joined by nearly 400 incredible people, all with the same vision. We've grown in other ways too – we raised $35m in our Series A funding round, and launched our game-changing authentication platform. Our technology is now being used by hundreds and thousands of users worldwide, including some of the world's leading financial institutions. And this is just the beginning.

A confusion matrix is a supervised machine learning evaluation tool that provides more insight into the overall effectiveness of a machine learning classifier. Unlike a simple accuracy metric, which is calculated by dividing the number of correctly predicted records by the total number of records, confusion matrices return 4 unique metrics for you to work with. While I am not saying accuracy is always misleading, there are times, especially when working with examples of imbalanced data, that accuracy can be all but useless. Let's consider credit card fraud. It is not uncommon that given a list of credit card transactions, that a fraud event might make up a little as 1 in 10,000 records.