Verified Data Mining Functionalities

               1. Descriptive mining task

               2. Predictive mining task

              1. Frequent Pattern

          Data mining functionalities are used to specify what kind of pattern are present in our data during data mining tasks.

We can further divide data mining tasks into two different categories.

1.     Descriptive mining task

2.     Predictive mining task

          In descriptive mining tasks we try to find out the general properties present in our data. For example, we find data describing patterns and come up with new and significant information present in our available dataset.

          In predictive mining tasks we try to find out some inference on the current data in order to make some predictions from the available data for the future.

          When we try to summarize some general characteristics or features present in our target class of data then it's known as Data Characterization. Whereas when we try to compare general features of target class data objects with the general features of objects form one or a set of contrasting classes then its known as Data Discrimination.

         While performing data mining we try to find out what frequent pattern is present in the data, is there any associations is present in our data and does our data have some correlation present in them.

          Here, we try to find out what are some frequent patterns present in our data. There are many kinds of frequent patterns present. Some of the present patterns are subsequences, item sets, and substructures.

          Association analysis is a type of analysis where we try to find out is there any association present in our data.

Let’s imagine, you are a store manager of a big mart, you want to find out that which items are frequently purchased together within the same transactions.

For example, we may know, most of the time bread and butter are purchased together, egg and bread are bought together.

Purchased (X, “bread”) = Purchased (X, “butter”) with support = 1% and confidence = 50%.

Here X represents a variable customer. Confidence = 505 means that is a customer purchase a bread, there is a 50% change that he/she will also buy butter.

Support = 1% means that from all the transactions taken under analysis bread and butter were purchased together in 1% of all the transactions.

            Classification is a process where we try to find a model that can describe and distinguishes data into different classes and then the model can be use for the prediction of the class of objects whose class label is unknown.

          When we try to divide our data into different clusters based on some similarity between the data points where we don’t have a target variable then it is known as Cluster Analysis or Clustering.

From the above figure, we can see that the data points are divided into three different clusters based on some similarities between the data points.

I hope after reading this article, finally, you came to know about what are some of the Verified data mining functionalities?

   

Like the Blog, then Share it with your friends and colleagues to make this AI community stronger. 

To learn more about nuances of Artificial Intelligence, Python Programming, Deep Learning, Data Science and Machine Learning, visit our insideAIML blog page.

Keep Learning. Keep Growing.