Data mining techniques and applications

---

Bharati M. Ramageri / Indian Journal of Computer Science and Engineering 
Vol. 1 No. 4 301-305 
DATA MINING TECHNIQUES AND APPLICATIONS 
Mrs. Bharati M. Ramageri, Lecturer 
Modern Institute of Information Technology and Research, 
Department of Computer Application, Yamunanagar, Nigdi 
Pune, Maharashtra, India-411044. 
 
 
Abstract 
Data mining is a process which finds useful patterns from large amount of data. The paper discusses few of the data mining 
techniques, algorithms and some of the organizations which have adapted data mining technology to improve their businesses and 
found excellent results. 
Keywords: Data mining Techniques; Data mining algorithms; Data mining applications. 
1. Overview of Data Mining 
The development of Information Technology has generated large amount of databases and huge data in 
various areas. The research in databases and information technology has given rise to an approach to store 
and manipulate this precious data for further decision making. Data mining is a process of extraction of 
useful information and patterns from huge data. It is also called as knowledge discovery process, 
knowledge mining from data, knowledge extraction or data /pattern analysis. 
Figure 1. Knowledge discovery Process 
Data mining is a logical process that is used to search through large amount of data in order to find 
useful data. The goal of this technique is to find patterns that were previously unknown. Once these 
patterns are found they can further be used to make certain decisions for development of their businesses.
Three steps involved are 

Exploration 

Pattern identification 

Deployment 
Exploration: In the first step of data exploration data is cleaned and transformed into another form, and 
important variables and then nature of data based on the problem are determined.
ISSN : 0976-5166
301

---

Bharati M. Ramageri / Indian Journal of Computer Science and Engineering 
Vol. 1 No. 4 301-305 
Pattern Identification: Once data is explored, refined and defined for the specific variables the second step 
is to form pattern identification. Identify and choose the patterns which make the best prediction.
Deployment: Patterns are deployed for desired outcome.