Data Mining Tutorial

Data Mining Tutorial Association Rule in Data Mining Data Mining Process Cluster Analysis in Data Mining Data Cleaning in Data Mining Data Mining Algorithms Difference between Data Warehouse and Data Mining Data Mining Tools Data Pre-processing in Data Mining Major Issues in Data Mining Clustering in Data Mining Data Mining Steps Data Mining Applications Data Mining Functionalities Data Mining Architecture Data Mining Techniques Data Mining Tasks Regression in Data Mining KDD in Data Mining Outlier Analysis in Data Mining Data Cleaning in Data Mining

Data Mining Functionalities
2021-01-19 12:03:57

Data Mining Functionalities

Data Mining Functionalities

The Data Mining functionalities are basically used for specifying the different kind of patterns or trends that are usually seen in data mining tasks. Data mining is extensively used in many areas or sectors. It is used to predict and characterize data. But the ultimate objective in Data Mining Functionalities is to observe the various trends in data mining.

Let us now first understand what is meant by Data Mining Tasks:

The Data Mining tasks can be categorized into two kinds:

  • Descriptive Data Mining
  • Predictive Data Mining
Data Mining Functionalities

Descriptive Data Mining:

This kind of Data Mining can be described as the mining that specifies the general properties of the data in the given database. In order words, we can say this kind of data mining task’s functions are known for dealing with the general properties of the data in the database.

Given below are functions listed in this kind of Data Mining:

  1. Class or Concept Description
  2. Mining of Frequent Patterns
  3. Mining of Associations
  4. Mining of Correlations
  5. Mining of Clusters

Class or Concept Description:

Class or Concept refers to the data that is linked or correlated with some classes or some concepts. For instance, let’s say there is a company and in that company, the classes of things for sales include mugs and glasses, and concepts of customers include big spenders and budget spenders. The types of descriptions of a class or a concept are known as class or concept descriptions. These descriptions can be acquired with the help of the ways listed below which are:

  • Data Characterization ? Data Characterization is a method which sums up a dataset of class under study. This class which is under study is known as Target Class.
  • Data Discrimination ? It means to classify a class with the help of some predefined group or class.

Mining of Frequent Patterns:

The second function in Descriptive Data Mining is the “Frequent patterns”. They can be defined as the patterns that takes place very often in transactional data, which are:

  • Frequent Item Set:  As the name suggest, the meaning of Frequent Item set is a set of items that are often appeared together. For instance, shoes and socks.
  • Frequent Subsequence:  Much similar to the above point, a sequence of patterns that takes place very often like putting on socks and then shoes is called Frequent Subsequence.
  • Frequent Sub Structure: Substructure is called different structural forms, for instances graphs, charts, etc. combined with subsequences.

Mining of Association:

Mining of Associations are mainly used in retail sales in order to identify patterns that are very often purchased together. The process of Mining of Association can be defined as the process of revealing the relationship among the set of data and finding out association rules.

Let us take an example for instance, let’s say a retailer generates an association rule that shows that over 80% of time an egg is sold with milk and only 20% of times biscuits are sold with milk.

Mining of Correlations:

Mining of Correlations refers to a type of Descriptive Data Mining’s Functions that are usually executed in order to reveal or expose some statistical correlations between associated attribute value pairs or between two item sets. This is helpful to analyze that whether they are having positive, negative or no effect on each other.

Mining of Clusters:

The literal meaning of the word “Cluster” is a group of things which are similar to one another in some way or another. Now coming to the term “Cluster analysis”, it means to form group of things that are almost alike each other but at the same time, they are very different from the things that are in other clusters.

Predictive Data Mining:

Predictive data mining refers to the kind of Data Mining can be described as the mining where inference on the current data is performed so that it makes certain predictions. Classification and the meaning of classification is a process of finding a model that describes the data classes or concepts. The model derived in the process are represented in various formations, the formations are listed below:

  • Decision Tree
  • Neutral Network

Decision Tree:

A decisiontree is a like a flow chart with a tree structure, in which every junction/node is used to represent a test on an attribute value, moreover, each and every branch is responsible for representing the concluding outcome of the test, and tree leaves are used to represent the classes or the distribution of classes.

Neural Network:

A neural network is mainly used for classification can be defined as a collection of processing units with connections between the units. In other and simpler words, Neural networks searches for patterns or trends in large quantity of different sets of data, which allows organizations to understand more and better about their clients or users need which is directly responsible for rendering their marketing strategies, increase sales and lowers costs.