In this article, we get an overview of data mining and understand its evolution. There are some fundamental question about data mining that every beginner wants to know. Therefore, we try to answer those questions as accurately as possible.
As we learn more, you will find that the data mining industry is growing into a new areas rapidly since there has been some new development in database systems industry.
What is the motivation behind Data Mining?
The business in older times did not accumulate much data. However, with the development of digital systems many new businesses are spread across many countries and customer all over the world. These new businesses are doing huge number of transactions year after year. There is a requirement of understanding the customer behavior, products and other statistical information from the historical data.
The database industry and information system technology is also growing at rapid pace and continuously evolving. Therefore, data mining is a result of this natural evolution and assist business to analyze data and get meaningful information to take important decisions.
Evolution of Data Mining
Let us understand how database system industry evolved into data mining industry.
OLTP vs OLAP
The businesses have two types of data repository. One is to manage day-to-day management of transaction from an OLTP (Online Transaction Processing) application.
When you book a ticket online, or query for availability of tickets is called a simple database transaction. The data is either retrieved from a RDBMS or stored to the RDBMS if the transaction follow ACID properties.
Withdrawing money from an ATM machine is another example of OLTP system. The user can see the available balance by querying the database and withdraw money.
The OLAP ( Online Analytical Processing ) system is one that provides a multi-dimensional analysis of the data from different data repositories and databases. One of these repositories is Data Warehouse.
What is Data Mining ?
Earlier we told you that data is growing at an exponential rate and this data contains rich information which we cannot use.
The data mining technology change this information into knowledge. Therefore, Data mining refers to extracting or ‘mining’ knowledge from large amount of data.
Some other names given to data mining is
- Knowledge mining from data
- Data or Pattern Analysis
- Knowledge Extraction
- Data Archeology
- Data Dredging
- KDD or Knowledge discovery from data