Chapter 1 Decision Trees
Section 1 Classification
Page 2 Classification

Objectives

The objectives of this section are:
to introduce you to the concept of classifications
to impart on you its usefulness in our society
to awaken you to the boundless applications
to excite you to delve deeper into the world of data mining

Outcomes

By the time you have completed this section you will be able to:
describe what classification is
determine when classification can be used

What is Classification?

About Section 1

This section gives a brief introduction to classification and the various uses it has in our society. The ability of the human mind to process information and group them has been applied in the field of computer science and its implications are far reaching.

Classification in the real world

On some level we do it intuitively. Our brains classify events, items and sometimes even people based on a particular set of attributes. For instance, late one night you are walking down an alley and see a well muscled man with a gun and a menacing glare approach you, almost everyone on this planet would try and get out of his path, our brain has classified him as dangerous. terminatorvsIPodgirl
Now what if you see a young teenage girl walking down that same alley, dancing to the music blaring from her iPod would you clutch your purse and run or just give her space and walk by? Most of us would opt for the later and that is because our brains have classified her as harmless.

In the same way, classification in data mining deals with grouping items into various predefined categories based on a list of attributes or characteristics provided.

 

 

Applications

Have you ever gone to BestBuy or Apple to purchase a new computer and your credit card was initially rejected and you had to call a 1-800 number to verify the purchase? This is classification at work. The influx of data has help propel the use of classification in many fields such as sales/marketing, medicine, financial markets, internet services, astronomy, anthropology and so on. Some applications of classification include

  1. Predicting tumor cells as benign or malignant
  2. Classifying credit card transactions as legitimate or fraudulent
  3. Categorizing news stories as finance, weather, entertainment, sports, etc.
  4. Detecting spam email messages based upon the message header and content
  5. Classifying galaxies based upon their shapes.

Types of Classifiers

There are different kinds of classification models (otherwise known as classifiers) that are used in various industries.

The remaining sections in this chapter focus on the Decision Tree Classifier.