Data Classification and Its Application in Credit Card Approval

We are all now living in the information age. The amount of data being collected by
businesses, companies and agencies is large. Recent advances in technologies to
automate and improve data collection have increased the volumes of data. Lying hidden
in all this data is potentially useful information that is rarely made explicit or taken
advantage of. In this context, data mining has arisen as an important research area that
helps to reveal the hidden useful information from the raw data collected. Many intensive
researches have been conducted to enhance the capability of data mining solution in
providing the intelligence so that different types of businesses can make informed
decisions.
This project demonstrates how data mining can address the need of business
intelligence in the process of decision-making. An analysis on the field of data mining is
done to show how data mining, especially data classification, can help in businesses such
as targeted marketing, credit card approval, fraud detection, medical diagnosis, and
scientific work. This project is involved with identification of the available algorithms
used in data classification and the implementation of C4.5 decision tree induction
algorithm in solving the data classifying task. Sample credit card approval dataset is used
to demonstrate the functionality of a data mining solution prototype, which includes the
typical tasks of a decision tree induction process: data selection, data preprocessing,
decision tree induction, tree pruning, rules generation and validation.
The result of this application using the sample credit card approval dataset
includes a decision tree, a set of rules derived from the decision tree and its accuracy.
These outputs help to identify the pattern of applicants who are more likely to be
accepted or rejected. The set of rules can be used as part of the knowledge base in expert
system or decision support system for financial institutions.