- Trending Categories
- Data Structure
- Networking
- RDBMS
- Operating System
- Java
- iOS
- HTML
- CSS
- Android
- Python
- C Programming
- C++
- C#
- MongoDB
- MySQL
- Javascript
- PHP

- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who

# What are the types of Outliers in data mining?

There are various types of outliers in data mining are as follows −

**Global Outliers** − In a given data set, a data object is a global outlier if it deviates essentially from the rest of the information set. Global outliers are known as point anomalies, and are the easiest type of outliers. Most outlier detection methods are aimed at discovering global outliers.

It can identify global outliers, an important issue is to discover an appropriate measurement of deviation concerning the application in question. There are several measurements are proposed, and, depends on these, outlier detection approaches are partitioned into multiple categories.

Global outlier detection is essential in several applications. Consider intrusion detection in computer networks, for instance, if the communication behavior of a computer is different from the normal designs (e.g., a huge number of packages is advertised in a short time), this behavior can be treated as a global outlier and the corresponding computer is a suspected casualty of hacking.

**Contextual Outliers** − Contextual outliers are called a Conditional outliers. These types of outliers appears if a data object deviates from the multiple data points because of some definite condition in a given data set.

There are two types of attributes of objects of data including contextual attributes and behavioral attributes. Contextual outlier analysis allows the users to determine outliers in multiple contexts and conditions, which can be beneficial in several applications.

In Behavioral attributes, it can represent the object’s characteristics, and are used to compute whether the object is an outlier in the context to which it understand. In the temperature instance, the behavioral attributes can be the temperature, moisture, and pressure.

Contextual outliers are a generalization of local outliers, a concept introduced in density-based outlier analysis methods. An object in a data set is a local outlier if its density essentially deviates from the local area in which it appears.

Global outlier detection can be concerned as a special method of contextual outlier detection where the group of contextual attributes is null. In other words, global outlier detection need the entire data set as the context. Contextual outlier analysis supports flexibility to users in that one can determine outliers in several contexts, which can be desirable in several applications.

**Collective Outliers** − In a given set of data, when a set of data points deviates from the rest of the information set is known as collective outliers. Therefore, the specific set of data objects cannot be outliers, but when it can consider the data objects as a whole, they can act as outliers.

It can recognize the types of multiple outliers, it is required to go through background data about the relationship among the behavior of outliers shown by multiple data objects.

- Related Questions & Answers
- What are the types of data mining models?
- What are the types of mining sequence data?
- What are the types of Clustering in data mining?
- What are the types of clusters in data mining?
- What are the types of regression in data mining?
- What are the types of Web Mining?
- What are the areas of text mining in data mining?
- What are the functionalities of data mining?
- What are the challenges of data mining?
- What are the applications of data mining?
- What are the features of data mining?
- What are the limitations of data mining?
- What are the components of data mining?
- What are the techniques of data mining?
- What are the tools of data mining?