Open AccessData mining algorithm for development of a predictive model for mitigating loan risk in Nigerian banks
Author(s) -
Olumuyiwa B. Alaba,
E.O. Taiwo,
O. Abass
Publication year - 2021
Publication title -
journal of applied science and environmental management
Language(s) - English
Resource type - Journals
eISSN - 2659-1499
pISSN - 2659-1502
DOI - 10.4314/jasem.v25i9.11
Subject(s) - c4.5 algorithm , loan , decision tree , computer science , naive bayes classifier , decision tree learning , decision tree model , data mining , algorithm , predictive modelling , machine learning , actuarial science , finance , business , support vector machine
The focus of this paper is on the development of data mining algorithm for developing of predictive loan risk model for Nigerian banks. The model classifies and predicts the risk involved in granting loans to customers as either good or bad loan by collecting data based on J48 decision tree, BayesNet and Naïve Bayes algorithms for a period of ten (10) years (2010 2019) from using structured questionnaire. The formulation and simulation of the predictive model were carried out using Waikato Environment for Knowledge Analysis (WEKA) software. The performance of the three algorithms for predicting loan risk was done based on accuracy and error rate metrics. The study revealed that J48 decision tree model is the most efficient of all the three models.