But you’re busyai??i??you don’t have time to watch KPI indicators all day long. That’s where Anomaly.io comes in. By combining our detection algorithms with your Salesforce data, you can automatically detect problems and notify the appropriate personnel to ensure that speedy corrective action is taken.
Category Archives: detection
Monitoring Key Performance Indicators (KPIs) is essential to running a successful business. As one example, you should examine your lead generation KPI several times a day, to allow you to detect and correct problems as quickly as possible.
Monitoring key performance indicators (KPIs), sales or any other product data means working within an ecosystem where very often you will see metrics correlating with each other. When a normal correlation between two metrics is broken, we have reason to suspect something strange is happening.
As an example, take a look at anomaly.ioAi??analytics during its early days (a long time ago). In the graphic above, the new users are shown in green and the returning users in red. Clearly, something strange happens in the middle of November. Let’s use some techniques to find out more!
Previously, we looked at using Twitter BreakoutAi??(EDM) to detect Anomalies.Ai??As with the popularAi??E-Divisive,Ai??EDM detects mean shift and changes in distribution. Both algorithms work with seasonal time series, but perform even better without seasonality. Read More
Time series decomposition splits a time series into seasonal, trend and randomAi??residual time series. TheAi??trend and the random time series can both be used to detect anomalies. But detecting anomalies in an already anomalous time series isn’t easy.
Our brains are really fast at recognizing patterns and forms: we can often find the seasonality of a signal in under a second. It is also possible do this with mathematics using the Fourier transform.
First, we will explain what a Fourier transform is. Next, we will find the seasonality of a website from its Google Analytics pageview report using the R language.
Monitored metrics very often exhibit regular patterns. When the values are correlated with the time of the day, it’s easier to spot anomalies, but it’s harder when they do not. In some cases, it is possible to use machine learning to differentiate the usual patterns from the unusual ones.
It isAi??common to monitor the number of events that occur in a period of time. Unfortunately, this technique isn’t fast, and can fail to detect some anomalies. The alternative is to change the problem to studyingAi??the period of time betweenAi??events.