Credit risk assessment using machine learning techniques

Varsha Aithal, Roshan David Jathanna

Research output: Contribution to journalArticle

Abstract

Analysis of credit scoring is an effective credit risk assessment technique, which is one of the major research fields in the banking sector. Machine learning has a variety of applications in the banking sector and it has been widely used for data analysis. Modern techniques such as machine learning have provided a self-regulating process to analyze the data using classification techniques. The classification method is a supervised learning process in which the computer learns from the input data provided and makes use of this information to classify the new dataset. This research paper presents a comparison of various machine learning techniques used to evaluate the credit risk. A credit transaction that needs to be accepted or rejected is trained and implemented on the dataset using different machine learning algorithms. The techniques are implemented on the German credit dataset taken from UCI repository which has 1000 instances and 21 attributes, depending on which the transactions are either accepted or rejected. This paper compares algorithms such as Support Vector Network, Neural Network, Logistic Regression, Naive Bayes, Random Forest, and Classification and Regression Trees (CART) algorithm and the results obtained show that Random Forest algorithm was able to predict credit risk with higher accuracy.

Original languageEnglish
Pages (from-to)3482-3486
Number of pages5
JournalInternational Journal of Innovative Technology and Exploring Engineering
Volume9
Issue number1
DOIs
Publication statusPublished - 11-2019
Externally publishedYes

Fingerprint

Risk assessment
Learning systems
Supervised learning
Learning algorithms
Logistics
Neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Civil and Structural Engineering
  • Mechanics of Materials
  • Electrical and Electronic Engineering

Cite this

Aithal, Varsha ; Jathanna, Roshan David. / Credit risk assessment using machine learning techniques. In: International Journal of Innovative Technology and Exploring Engineering. 2019 ; Vol. 9, No. 1. pp. 3482-3486.
@article{c92ada76e0f34a8383c3ff462028c72a,
title = "Credit risk assessment using machine learning techniques",
abstract = "Analysis of credit scoring is an effective credit risk assessment technique, which is one of the major research fields in the banking sector. Machine learning has a variety of applications in the banking sector and it has been widely used for data analysis. Modern techniques such as machine learning have provided a self-regulating process to analyze the data using classification techniques. The classification method is a supervised learning process in which the computer learns from the input data provided and makes use of this information to classify the new dataset. This research paper presents a comparison of various machine learning techniques used to evaluate the credit risk. A credit transaction that needs to be accepted or rejected is trained and implemented on the dataset using different machine learning algorithms. The techniques are implemented on the German credit dataset taken from UCI repository which has 1000 instances and 21 attributes, depending on which the transactions are either accepted or rejected. This paper compares algorithms such as Support Vector Network, Neural Network, Logistic Regression, Naive Bayes, Random Forest, and Classification and Regression Trees (CART) algorithm and the results obtained show that Random Forest algorithm was able to predict credit risk with higher accuracy.",
author = "Varsha Aithal and Jathanna, {Roshan David}",
year = "2019",
month = "11",
doi = "10.35940/ijitee.A4936.119119",
language = "English",
volume = "9",
pages = "3482--3486",
journal = "International Journal of Innovative Technology and Exploring Engineering",
issn = "2278-3075",
publisher = "Blue Eyes Intelligence Engineering and Sciences Publication",
number = "1",

}

Credit risk assessment using machine learning techniques. / Aithal, Varsha; Jathanna, Roshan David.

In: International Journal of Innovative Technology and Exploring Engineering, Vol. 9, No. 1, 11.2019, p. 3482-3486.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Credit risk assessment using machine learning techniques

AU - Aithal, Varsha

AU - Jathanna, Roshan David

PY - 2019/11

Y1 - 2019/11

N2 - Analysis of credit scoring is an effective credit risk assessment technique, which is one of the major research fields in the banking sector. Machine learning has a variety of applications in the banking sector and it has been widely used for data analysis. Modern techniques such as machine learning have provided a self-regulating process to analyze the data using classification techniques. The classification method is a supervised learning process in which the computer learns from the input data provided and makes use of this information to classify the new dataset. This research paper presents a comparison of various machine learning techniques used to evaluate the credit risk. A credit transaction that needs to be accepted or rejected is trained and implemented on the dataset using different machine learning algorithms. The techniques are implemented on the German credit dataset taken from UCI repository which has 1000 instances and 21 attributes, depending on which the transactions are either accepted or rejected. This paper compares algorithms such as Support Vector Network, Neural Network, Logistic Regression, Naive Bayes, Random Forest, and Classification and Regression Trees (CART) algorithm and the results obtained show that Random Forest algorithm was able to predict credit risk with higher accuracy.

AB - Analysis of credit scoring is an effective credit risk assessment technique, which is one of the major research fields in the banking sector. Machine learning has a variety of applications in the banking sector and it has been widely used for data analysis. Modern techniques such as machine learning have provided a self-regulating process to analyze the data using classification techniques. The classification method is a supervised learning process in which the computer learns from the input data provided and makes use of this information to classify the new dataset. This research paper presents a comparison of various machine learning techniques used to evaluate the credit risk. A credit transaction that needs to be accepted or rejected is trained and implemented on the dataset using different machine learning algorithms. The techniques are implemented on the German credit dataset taken from UCI repository which has 1000 instances and 21 attributes, depending on which the transactions are either accepted or rejected. This paper compares algorithms such as Support Vector Network, Neural Network, Logistic Regression, Naive Bayes, Random Forest, and Classification and Regression Trees (CART) algorithm and the results obtained show that Random Forest algorithm was able to predict credit risk with higher accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85075153089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075153089&partnerID=8YFLogxK

U2 - 10.35940/ijitee.A4936.119119

DO - 10.35940/ijitee.A4936.119119

M3 - Article

AN - SCOPUS:85075153089

VL - 9

SP - 3482

EP - 3486

JO - International Journal of Innovative Technology and Exploring Engineering

JF - International Journal of Innovative Technology and Exploring Engineering

SN - 2278-3075

IS - 1

ER -