Customer Payment Trend Analysis based on Clustering for Predicting the Financial Risk of Business Organizations

Text Sample:
Chapter 3:
METHODOLOGY:
3.1 Partitioning Method:
There exists a large number of clustering algorithms. The choice of clustering algorithm depends on type of data available and on the particular purpose and application. The method used to identify the clusters in this research is the partitioning method.
Given a database of n objects or data tuples, a partitioning method constructs k-partitions of the data, where each partition represents a cluster and k=n. that is it classifies the data into k groups which together satisfies the following requirements.
1. Each group must contain at least one object.
2. Each object must belong to exactly one group.
Given k, the number of partitions to construct, a partitioning method creates an initial partitioning. It then uses an iterative relocation technique that attempts to improve the partitioning by moving objects from one group to another. The general criterion of a good partitioning is that objects in the same cluster are close or related to each other whereas objects of different clusters are far apart or very different. There are various kinds of other criteria for judging the quality of partitions.
To achieve global optimality in partitioning based clusterring would require the exhaustive enumeration of all possible partitions. Most applications adopt one of two popular heuristic methods [1].
1. K-means algorithm, where each cluster is represented by the mean value of the objects in the cluster.
2. K-medoids algorithm, where each cluster is represented by one of the objects located near the center of the cluster. These heuristic clustering methods work well for finding spherical-shaped clusters in small to medium sized databases. To find clusters with complex shapes and for clustering very large data sets, partitioning methods need to be extended.
In this research, K-means algorithm is used for clustering as it was found most suitable.
3.2 K-means Algorithm for Partitioning:
The K-means

Prof. Jeeva Jose erned a PhD in Computer Science from Mahatma Gandhi University, Kerala, India and is a faculty member at BPC College, Kerala. Her passion is teaching and her areas of interest include World Wide Web, Data Mining and Cyber laws. She has been in higher education for the last 16 years and has completed three research projects funded by UGC and KSCSTE so far.
Hitherto, the author has authored and published three books. She has also published more than twenty research papers in various refereed journals and conference proceedings. She has edited three books and has held many speeches on various conferences. She is a recipient of an ACM-W Scholarship provided by the Association for Computing Machinery, New York.