Author: Yoel Zeldes

11 Oct Detecting Anomalies in a SMART Way – Part 3

In the first post of this series I described how we at Fortscale use a personalized adaptive threshold for triggering alerts. Each user’s activity is assigned a risk score (known as the SMART value) that triggers a SMART alert when it crosses the user’s threshold. We explained how the more anomalous activities a user performs through time, the higher his...

Read More

20 Sep Detecting Anomalies in a SMART Way – Part 2

In the previous post of this series I described how we at Fortscale use a personalized adaptive threshold for triggering alerts. Each user’s activity is assigned a risk score (known as the SMART value) that triggers a SMART Alert when crosses the user’s threshold. We explained how  the more anomalous activities a user performs through time, the higher his threshold...

Read More

26 Jul Detecting Anomalies in a SMART Way – Part 1

Detecting anomalous user behavior is hard. Really hard. Here at Fortscale we show that with the right tools, it’s doable. Our data science team has developed a set of self tuning machine learning based algorithms that aim at doing exactly that. Although the algorithms may be complicated to comprehend, their basic mechanism is easy to understand. The fortscale product contains many...

Read More