Using Cutting-Edge Tree-Based Stochastic Models to Predict Credit Risk

Khaled Halteh, Kuldeep Kumar, Adrian Gepp

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)
65 Downloads (Pure)

Abstract

Credit risk is a critical issue that affects banks and companies on a global scale. Possessing the ability to accurately predict the level of credit risk has the potential to help the lender and borrower. This is achieved by alleviating the number of loans provided to borrowers with poor financial health, thereby reducing the number of failed businesses, and, in effect, preventing economies from collapsing. This paper uses state-of-the-art stochastic models, namely: Decision trees, random forests, and stochastic gradient boosting to add to the current literature on credit-risk modelling. The Australian mining industry has been selected to test our methodology. Mining in Australia generates around $138 billion annually, making up more than half of the total goods and services. This paper uses publicly-available financial data from 750 risky and not risky Australian mining companies as variables in our models. Our results indicate that stochastic gradient boosting was the superior model at correctly classifying the good and bad credit-rated companies within the mining sector. Our model showed that ‘Property, Plant, & Equipment (PPE) turnover’, ‘Invested Capital Turnover’, and ‘Price over Earnings Ratio (PER)’ were the variables with the best explanatory power pertaining to predicting credit risk in the Australian mining sector.
Original languageEnglish
Article number55
Number of pages13
JournalRisks
Volume6
Issue number2
DOIs
Publication statusPublished - 16 May 2018

Fingerprint

Credit risk
Stochastic model
Turnover
Boosting
Gradient
Methodology
Financial data
Decision tree
Loans
Credit
Financial health
Mining industry
Credit risk modeling

Cite this

@article{ea2979e0e1654fb1afc0ade37041f90d,
title = "Using Cutting-Edge Tree-Based Stochastic Models to Predict Credit Risk",
abstract = "Credit risk is a critical issue that affects banks and companies on a global scale. Possessing the ability to accurately predict the level of credit risk has the potential to help the lender and borrower. This is achieved by alleviating the number of loans provided to borrowers with poor financial health, thereby reducing the number of failed businesses, and, in effect, preventing economies from collapsing. This paper uses state-of-the-art stochastic models, namely: Decision trees, random forests, and stochastic gradient boosting to add to the current literature on credit-risk modelling. The Australian mining industry has been selected to test our methodology. Mining in Australia generates around $138 billion annually, making up more than half of the total goods and services. This paper uses publicly-available financial data from 750 risky and not risky Australian mining companies as variables in our models. Our results indicate that stochastic gradient boosting was the superior model at correctly classifying the good and bad credit-rated companies within the mining sector. Our model showed that ‘Property, Plant, & Equipment (PPE) turnover’, ‘Invested Capital Turnover’, and ‘Price over Earnings Ratio (PER)’ were the variables with the best explanatory power pertaining to predicting credit risk in the Australian mining sector.",
author = "Khaled Halteh and Kuldeep Kumar and Adrian Gepp",
year = "2018",
month = "5",
day = "16",
doi = "10.3390/risks6020055",
language = "English",
volume = "6",
journal = "Risks",
issn = "2227-9091",
publisher = "MDPI",
number = "2",

}

Using Cutting-Edge Tree-Based Stochastic Models to Predict Credit Risk. / Halteh, Khaled; Kumar, Kuldeep; Gepp, Adrian.

In: Risks, Vol. 6, No. 2, 55, 16.05.2018.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Using Cutting-Edge Tree-Based Stochastic Models to Predict Credit Risk

AU - Halteh, Khaled

AU - Kumar, Kuldeep

AU - Gepp, Adrian

PY - 2018/5/16

Y1 - 2018/5/16

N2 - Credit risk is a critical issue that affects banks and companies on a global scale. Possessing the ability to accurately predict the level of credit risk has the potential to help the lender and borrower. This is achieved by alleviating the number of loans provided to borrowers with poor financial health, thereby reducing the number of failed businesses, and, in effect, preventing economies from collapsing. This paper uses state-of-the-art stochastic models, namely: Decision trees, random forests, and stochastic gradient boosting to add to the current literature on credit-risk modelling. The Australian mining industry has been selected to test our methodology. Mining in Australia generates around $138 billion annually, making up more than half of the total goods and services. This paper uses publicly-available financial data from 750 risky and not risky Australian mining companies as variables in our models. Our results indicate that stochastic gradient boosting was the superior model at correctly classifying the good and bad credit-rated companies within the mining sector. Our model showed that ‘Property, Plant, & Equipment (PPE) turnover’, ‘Invested Capital Turnover’, and ‘Price over Earnings Ratio (PER)’ were the variables with the best explanatory power pertaining to predicting credit risk in the Australian mining sector.

AB - Credit risk is a critical issue that affects banks and companies on a global scale. Possessing the ability to accurately predict the level of credit risk has the potential to help the lender and borrower. This is achieved by alleviating the number of loans provided to borrowers with poor financial health, thereby reducing the number of failed businesses, and, in effect, preventing economies from collapsing. This paper uses state-of-the-art stochastic models, namely: Decision trees, random forests, and stochastic gradient boosting to add to the current literature on credit-risk modelling. The Australian mining industry has been selected to test our methodology. Mining in Australia generates around $138 billion annually, making up more than half of the total goods and services. This paper uses publicly-available financial data from 750 risky and not risky Australian mining companies as variables in our models. Our results indicate that stochastic gradient boosting was the superior model at correctly classifying the good and bad credit-rated companies within the mining sector. Our model showed that ‘Property, Plant, & Equipment (PPE) turnover’, ‘Invested Capital Turnover’, and ‘Price over Earnings Ratio (PER)’ were the variables with the best explanatory power pertaining to predicting credit risk in the Australian mining sector.

UR - http://www.scopus.com/inward/record.url?scp=85056721036&partnerID=8YFLogxK

U2 - 10.3390/risks6020055

DO - 10.3390/risks6020055

M3 - Article

VL - 6

JO - Risks

JF - Risks

SN - 2227-9091

IS - 2

M1 - 55

ER -