The application of data mining techniques to support customer relationship management: the case of ethiopian revenue and customs authority

TL;DR

This paper applies data mining techniques, specifically decision trees and neural networks, to classify customers of the Ethiopian Revenue and Customs Authority, achieving high accuracy to enhance customer relationship management.

Contribution

It demonstrates the effectiveness of decision tree and neural network models in classifying ERCA customers with high accuracy, aiding CRM strategies.

Findings

Decision tree model achieved 99.95% accuracy.

ANN model achieved 99.71% accuracy.

Decision tree outperformed ANN in classification accuracy.

Abstract

The application of data mining technique has been widely applied in different business areas such as health, education and finance for the purpose of data analysis and then to support and maximizes the organizations customer satisfaction in an effort to increase loyalty and retain customers business over their lifetimes . The researchers primary objective, in this paper is to classify customers based on their common attributes since customer grouping is the main part of customer relationship management. In this study, different characteristics of the ERCA customers data were collected from the customs database called ASYCUDA. Once the customers data were collected, the necessary data preparation steps were conducted on it and finally a data set consisting of 46748 records was attained. The classification modeling was built by using J48 decision tree and multi layer perceptron ANN algorithms with 10-fold cross-validation and splitting (70% training and 30% testing) techniques. Among these models, a model which was built using J48 decision tree algorithm with default 10-fold cross-validation outperforms 99.95% of overall accuracy rate; while the classification accuracy of ANN is 99.71%. So decision tree has better accuracy than ANN for classifying ERCA customers data.