Beginning Anomaly Detection Using

 Categories  of Anomalies

Now that you have some perspective of what anomalies can be in various situations, you 

can see that they generally fall into these broad categories:

•  Data point-based anomalies

•  Context-based anomalies

•  Pattern-based anomalies

Figure 1-15.  Number of pickups for a taxi company throughout the year, with a 

polar vortex hitting the city in April

Chapter 1   What Is anomaly DeteCtIon?

---

16

 Data Point-Based Anomalies

Data point-based anomalies can seem comparable to outliers in a set of data points. 

However, anomalies and outliers are not the same thing. 

Outliers are data points that are 

expected to be present in the data set and can be caused by unavoidable random errors 

or from systematic errors relating to how the data was sampled. 

Anomalies are outliers 

or other values that one doesn’t expect to exist. These types of anomalies can be found 

wherever a data set of values exists.

An example of this is a data set of thyroid diagnostic values, where the majority of 

the data points are indicative of normal thyroid functionality. In this case, anomalous 

values represent sick thyroids. While they are not necessarily outliers, they have a low 

probability of existing when taking into account all the normal data.

You can also detect individual purchases totaling to excessive amounts and label 

them as anomalies since, by definition, they are not expected to occur or have a very low 

probability of occurrence. In this case, they are labeled as fraud transactions, and the 

card holder is contacted to ensure the validity of the purchase.

Basically, you can say this about the difference between anomalies and outliers: you 

should expect there to be outliers in a set of data, but not anomalies.