Abstract: | The global banking industry is facing more competition than ever before. Banks must attend to fulfill the wants and desires of their clients to maintain a competitive advantage in the market.
Segmenting customers is one of the best ways to interact with them. Because of applying of data mining clustering technologies, customer segmentation can assist banks in identifying more effective marketing tactics for the segments.
By treating the customer segments according to their transactional events (such as customer location, customer dob, customer gender, customer account balance, transaction date, and transaction amount), the unsupervised clustering technique is used in this thesis to segment Awash Bank customers to retain current customers, attract potential customers and improve customer service delivery processes.
The being of clustering segments, the acquire data is clean and preprocess in an aggregated data style. WEKA knowledge discovery software is utilize for data mining using clustering algorithms, such as k-means, density-base, and filter clusters. Experimental result shows k-means, filtered, density-based clustering algorithms separate the algorithmic result into two clusters based on the given attributes, such as customer gender, transaction amount, and customer account balance. The finding of the study is putting the whole bank customers into two clusters base on the given attributari
This study, the performance is execute to apply customer segmentation for Awash Bank is an input for the bank customer prediction. Further study can create a customer prediction model that improves customer relationship management based on the clustering result. |