Aveneu Park, Starling, Australia

Clustering- this research a new method is proposed for

Clustering- It involves identifying clusters and grouping similar objects
together in each cluster. The main focus is on evaluating and implementing
Partitioned (K-means) algorithms, other clustering methods include Hierarchical
(CURE, BIRCH), Grid – based (STING, WaveCluster), Model-based (Cobweb), and
Density based (DBSCAN). Author 31 presented work to enhance the performance
of one of the most well-known popular clustering algorithms (K-mean) to produce
near-optimal decisions for telcoschurn prediction and retention problems. Due
to its performance in clustering massive data sets. The final clustering result
of the k-mean clustering algorithm greatly depends upon the correctness of the
initial centroids, which are selected randomly. This research will be followed
by a serious of researches targeting the main objective which is an efficient
DSS which will be applied on customer banking data. In this research a new
method is proposed for finding the better initial centroids to provide an
efficient way of assigning the data points to suitable clusters with reduced
time complexity. The k-mean clustering algorithm is more prominent since its
intelligence to cluster massive data rapidly and efficiently. However, k-mean
algorithm is highly precarious in initial cluster centers. Because of the
initial cluster centers produced arbitrarily, k-mean algorithm does not promise
to produce the peculiar clustering results. Efficiency of the original k-mean
algorithm heavily rely on the initial centroids. Initial centroids also have an
influence on the number of iterations required while running the original
k-mean algorithm. The computational complexity of the original k-mean algorithm
is very high, specifically for massive data sets. Various methods have been
proposed in the literature to enhance the accuracy and efficiency of the k-mean
clustering algorithm. The drawbacks of k-mean as – its’ performance depends
highly on initial cluster centers, the number of clusters must be previously
known and fixed, and the algorithm contains the dead-unit problem which results
in empty clusters. Random k-mean initialization generally leads k-mean to
converge to local minima i.e. inacceptable clustering results are produced.


I'm Darlene!

Would you like to get a custom essay? How about receiving a customized one?

Check it out