A Hybrid Meta-Learner Technique for Credit Scoring of Banks’ Customers
Journal Title: Engineering, Technology & Applied Science Research - Year 2017, Vol 7, Issue 5
Abstract
Financial institutions are exposed to credit risk due to issuance of consumer loans. Thus, developing reliable credit scoring systems is very crucial for them. Since, machine learning techniques have demonstrated their applicability and merit, they have been extensively used in credit scoring literature. Recent studies concentrating on hybrid models through merging various machine learning algorithms have revealed compelling results. There are two types of hybridization methods namely traditional and ensemble methods. This study combines both of them and comes up with a hybrid meta-learner model. The structure of the model is based on the traditional hybrid model of ‘classification + clustering’ in which the stacking ensemble method is employed in the classification part. Moreover, this paper compares several versions of the proposed hybrid model by using various combinations of classification and clustering algorithms. Hence, it helps us to identify which hybrid model can achieve the best performance for credit scoring purposes. Using four real-life credit datasets, the experimental results show that the model of (KNN-NN-SVMPSO)-(DL)-(DBSCAN) delivers the highest prediction accuracy and the lowest error rates.
Authors and Affiliations
A. G. Armaki, M. F. Fallah, M. Alborzi, A. Mohammadzadeh
Keywords
Related Articles
- EP ID EP154762
- DOI -
- Views 242
- Downloads 0
Synthesis and Mechanical Characterization of High Density Polyethylene/Graphene Nanocomposites
The purpose of this work is to investigate the effects of graphene nanosheets (GNSs) addition on the mechanical and thermal properties of high density polyethylene (HDPE). The HDPE/Graphene nanocomposites were synthesize...
Cloud Masking for Remotely Sensed Data Using Spectral and Principal Components Analysis
Two methods of cloud masking tuned to tropical conditions have been developed, based on spectral analysis and Principal Components Analysis (PCA) of Moderate Resolution Imaging Spectroradiometer (MODIS) data. In the spec...
Two-dimensional Analysis of Cracks Propagation in Structures of Concrete
In this article we present a numerical simulation that allows describing and studying the damage of concrete works subjected to various stress types. In this study, the propagation of cracks in the concrete is analyzed a...
A Comparison Among Different Parameters for the Design of a Photovoltaic/Thermal System Using Computational Fluid Dynamics
The purpose of this paper is to compare several fins, duct height, and velocity magnitudes to acquire a PhotoVoltaic/Thermal system designed through Computational Fluid Dynamics. Simulation of different fins (rectangular...
A 4-4.8GHz Adaptive Bandwidth, Adaptive Jitter Phase Locked Loop
A low power, low phase noise adaptive bandwidth phase locked loop is presented in this paper. The proposed structure benefits from a novel lock status monitor unit (LSMU) that determines loop operation and loop bandwidth...