A Study On Semi Automatic Dm Technique For Discovering Meaningful Relationships From A Given Data Set

1693 Words Jan 22nd, 2015 7 Pages
CHAPTER TWO
2.1 Introduction
The term DM was conceptualised as early as 1990s as a means of addressing the problem of analysing the vast repositories of data that are available to mankind, and being added to continuously. DM has been the oldest yet one of the interesting buzzwords. It involves defining associations, or patterns, or frequent item sets, through the analysis of a given data set. Further-more, the discovered knowledge should be valid, novel, useful, and understandable to the user. Many organizations often underutilize their already existing databases not knowing that there is slot of hidden information that requires to be discovered i.e. interesting patterns or knowledge from these databases. DM disciplines revolve around statistics, artificial intelligence, and pattern recognition. There are two main techniques in DM that is reporting and DM techniques. Our study focuses on semi-automatic DM technique for discovering meaningful relationships from a given data set. There is no hypothesis required to mine the data (Jans 09). The technique uses exploratory analysis with no predetermined notions about what will constitute an ―interesting outcome (Kantardzi 02).

Our research is to apply DM on a given data set extracted from data held in RMIS at JKUAT. The literature review on the methodology used is presented in this chapter under Section 2.4. Before this we have the definition of terms in DM given in section 2.2 defining data mining, concept of knowledge…
Open Document