PROJECT REPORT

(Submitted for the Degree of B.Com (Hons) in Accounting and Finance under the University of Calcutta)

On

Credit risk management in banks : opportunities and

Challenges
Submitted by
Name of the Candidate : Sudipa Golui
Registration no: 412-1211-0360-21
CU Roll no: 211412-11-0021
College Roll No : DCH/100/21
Name of the College

Shibpur dinobundhoo institution (College)

Supervised by

Name of the supervisor : DR. SUSANTA KANRAR

(ASST. PROF. OF DEPT. OF COMMERCE)

Month of Submission

University of calcutta
 INDEX
Serial no topics page no

1.1 Introduction
1.2 Literature review
1.3 Objectives of
study

1.4 Research
Methodology
1.5 Limitations of Study
1.6 Chapter planning

2.1 Conceptual frame

work
 INTRODUCTION

Credit risk refers to the probability of loss due to a borrower’s failure to make payments on any type of debt.
Credit risk management is the practice of mitigating losses by assessing borrowers’ credit risk – including
payment behavior and affordability. This process has been a longstanding challenge for financial
institutions.

Continued global economic crises, ongoing digitalization, recent developments in technology and the
increased use of artificial intelligence in banking have kept credit risk management in the spotlight. As a
result, regulators continue to demand transparency and other improved capabilities in this space. They want
to know that banks have a thorough knowledge of customers and their associated credit risk. And as Basel
regulations evolve, banks will face an even bigger regulatory burden.

The opportunities of credit risk management are as follows :

Ensure Regulatory Complience :

Banks must comply with various regulatory requirements and guidelines set by finalcial authorities and
regulators. These regulators often dictate the capital adequacy requirements, provisioning norms and the
risk assesment standards, that banks must follow. Effective Credit Risk Management helps the bank
adhere to these regulations, avoiding legal penalties and ensuring that they maintain adequate capital
buffers to cover potential credit losses.

Minimize potential losses :

The foremost objective is to minimize potential losses arising from the default of borrowers. This involves
assessing the creditworthiness of borrowers before lending. Setting appropriate credit limits and monitoring
the borrower’s finalcial health regularly. Effective credit risk management ensures that banks exposure to
bad loans kept to a minimum, thereby protecting it’s assets quality and finalcial health.

Optimize Risk - Adjusted Returns :

Another key objective is to optimize the risk- adjusted returns on the bank’s lending portfolio. The involves
balancing the risk and return by setting appropriate interest rates, fees and other terms of lending.
Byeffectively managing credit risk, banks can achive higher return on their assests while maintaining
acceptable levels of risk. This contributes to the overall profitability and long term sustainability of the bank.
Although challanges are to be faced in this process are :

1 . Increasingly complex regulatory requirements:

Banks must navigate a constantly evolving regulatory landscape, frequently introducing new
rules and requirements. Failure to comply with these regulations can result in significant
financial and reputational damage. GDS Link’s solutions provide a comprehensive approach to
regulatory compliance, ensuring that banks stay ahead of the curve and avoid costly penalties

2 . Rapidly changing market conditions: The

financial industry is constantly in flux, with market conditions changing rapidly and frequently.
Banks must be able to adapt to these changes quickly to minimize risk and maximize returns.
GDS Link’s dynamic and flexible solutions enable institutions to respond quickly to changing
market conditions, ensuring they are always well-positioned to manage their credit risk.

3. Cybersecurity risks:
Cybersecurity threats are a growing concern for banks and other financial institutions, with the
potential to cause significant financial and reputational damage. GDS Link’s robust security
measures ensure that all data and systems are protected from cyber threats, giving banks
peace of mind and allowing them to focus on their core business.

4.Economic downturns :

Economic downturns can majorly impact credit risk management, with default rates increasing
and credit quality deteriorating. GDS Link’s risk management solutions are designed to help
institutions weather economic downturns, providing advanced modeling and analytics capabilities
that enable them to anticipate and mitigate the effects of an economic slowdown.Despite having
the above stated challenges Credit Risk Management in Banking System helps the finalcial
institutions to mitigate potential losses resulting from borrower defaults or credit events. In today’s
dynamic finalcial landscape, where uncertainities abound , effective credit risk management has
become crucial than ever.
Literature Review :
The year period 2003 to 2004 saw a number of banks being forced to close down in what
was termed the Zimbabwean Banking Crisis and the main cause being poor credit risk
management. In Zimbabwe the number of financial institutions declined from forty as at 31
December 2003 to twenty nine (29) as at 31 December 2004 and the impact of effective credit risk
management on bank survival cannot be overemphasized. Some financial institutions were forced
to close down and others were placed under curatorship.

The main cause of the banking crisis was poor credit risk management practices typified by
high levels of insider loans, speculative lending, and high concentration of credit in certain sectors
among other issues.The failure to effectively manage credit risk created similar problems in
counties such as Mexico and Venezuela.Reserve bank of Zimbabwe (RBZ),Bessis,
Markowitz ,Margrabe and Gakure et al. stated their opinion towards Credit Risk Management .
According to the Reserve bank of Zimbabwe (RBZ) risk management operating document (2004),
credit risk or default risk involves inability or unwillingness of a customer or counterparty to meet
commitments in relation to lending, trading, hedging, settlement and other financial
transactions.Bessis also includes a decline in the credit standing of counterparty as part of credit
risk. Credit risk management covers both the decision making process, before the credit decision
is made, and the follow-up of credit commitments, plus all monitoring and reporting
processes.According to Markowitz’s , he asserts that there are four steps in the construction of
portfolio as: security valuation, asset allocation, portfolio optimization and the performance
management. According to the theory, many companies use models for value at risk to manage
market risk and interest rate risk exposures According to Margrabe (2007), in spite of credit risk
remaining the significant risk that faces most SACCOs, the habit of utilizing this theory to credit
risk management is yet to be fully embraced. The theory, hence, seeks to bring forth the
significance of credit risk management for the SACCOs(Savings and Credit Cooperative
Societies)to remain efficient. Gakure et al. (2012) stated that the basis of the asset-by asset
approach is a sound loan appraisal and effective internal credit risk rating systems. Using this
approach, a loan appraisal and credit risk rating system allows the management to establish key
changes in an individual’s credits, or portfolio on time.
 Objective of Study
1.The primary objective of the analysis of credit risk is to reduce the default returns and to
maximize returns.

2.Credit Analysts use different kinds of financial techniques to measure credit risk. These
techniques include ratio analysis, trend analysis, etc. These techniques help the banks measure
the changing creditworthiness of the borrower and thus evaluate the potential of credit loss. Credit
Analysts play an important role in banks by helping them analyze their loan borrowers and reduce
the risk of defaults. They help save the money of the bank and in fact, increase it skillfully through
identifying good loan borrowers.

Data And Methodology:

This study is based on secondary data collected from literature available on this field in the forms
of books journals, published articles, authentic websites , and other relevant sources.
Limitations of Study:

Undertaking a project on credit risk management can be highly insightful and valuable, but it also
comes with several limitations. Here are some key challenges and limitations:
Data Accuracy and Reliability:
The study heavily relies on the accuracy and reliability of the financial data provided by both banks. Any
inaccuracies or inconsistencies in the data can significantly impact the findings and conclusions of the analysis.

External Factors:
Economic conditions, regulatory changes, industry trends, and market dynamics can influence the financial
performance of banks. It's challenging to isolate the impact of these external factors on the comparative
analysis accurately.

Uncertainity of accuracy :
All the informations relating to credit risk management collected from internet and relevent books, the
informations which are collected lead to uncertainty of accuracy even despite having too much informations.

Limited access to data :

Accessing comprehensive and accurate data on credit histories, financial statements, and other
relevant information can be difficult due to privacy laws and proprietary data restrictions.

Data Quality :
Inconsistent, incomplete, or outdated data can affect the accuracy of risk assessments and the
development of effective risk models.

Model Complexity:
Credit risk models, such as those based on statistical methods or machine learning, can be highly
complex and require significant expertise to develop and validate.

Interpritability:
 Advanced models, particularly those using machine learning techniques, can be difficult to
interpret and explain to stakeholders, which can hinder their acceptance and implementation.

Changing Regulations:The regulatory environment is dynamic, and frequent changes can require
continuous updates to risk management strategies and systems.

Economic Volatility:Economic downturns, market volatility, and unexpected events (e.g., financial
crises, pandemics) can significantly impact credit risk profiles and complicate risk management
efforts.
Assumption Validity :Many credit risk models rely on historical data and assumptions that may not
hold true in changing economic condition.

Cybersecurity Risks:
Protecting sensitive financial data from cyber threats is critical and challenging, with potential
breaches posing significant risks to data integrity and trust.nging economic condition.

Ackonledging the limitations can sensitively solve the problem relating to credit risk
management. Through this way credit risk management system can adopt by banks also can
provide facilities by banks.
 Conceptual Framework

Concept of Credit Risk Management :

Credit risk, or the risk that money owed is not repaid, has been prevalent in banking
history. It is a principal and perhaps the most important risk type that has been present in
finance, commerce and trade transactions from ancient cultures till today. Numerous small and
large failures, combined with the corresponding economic and social impact, further
accelerated the importance of credit risk management throughout history.Credit risk
management is a process that involves the identification of potential risks, the measurement of
these risks, the appropriate treatment, and the actual implementation of risk models.
Credit risk management is the process of identifying, assessing, and mitigating the risk of
losses that may arise from the failure of a borrower or counterparty to meet their financial
obligations. This is a crucial function for financial institutions, such as banks and investment
firms, as it helps ensure the stability and profitability of their operations. Here are the key
elements of credit risk management.

In other words it can be said that, credit risk management is the process of deep diving
into the borrower’s current and historical financial data for details about their financial
behavior including past debts, repayment, loan periods, and much more. Credit risk
management is an ongoing process in the borrower’s journey to examine credit risk according
to their financial behavior.

A picture has been depicted to make the concept easier

Customer Satisfaction
 About the concept Customer Satisfaction :

This study investigates the effect of credit risk management on customer satisfaction in
tier-one deposits money banks (DMBs) in Adamawa state, Nigeria. The objectives of the study
were to examine relationship between credit risk management and customers’ satisfaction and
to assess the relationship between credit risk management and credit appraisal process. The
study surveyed 384 selected customers from three tier-one DMBs in Adamawa state, Nigeria.
Purposive sampling was used in selecting the banks and simple random sampling was used in
administering the questionnaire to the customers. Descriptive and inferential statistics were

used to analyze and interpret the data collected. The study found that there is positive and
significant relationship between credit risk management and customer satisfaction and the
regression results showed that 49% of the variability in customer satisfaction can be explained
by credit risk management. The study also found signicant positive correlation between credit
appraisal process and credit risk management, with 81% of the variability in credit appraisal
process explained by credit risk management. The study recommends that despite the positive
relationship between credit risk management and customer satisfaction, there is need for
banks’ management to pay attention to other factors that will contribute to customer
satisfaction other than granting of credit facilities. At intervals, Banks should conduct seminars
or training to update their staff on current credit guidelines issue regulatory authorities to
enhance their knowledge on credit risk management with a view to ensuring Customer
satisfaction. Customer is a person having attitude of interacting in regular banking business

and can be inferred hence, that banking business is based on customers (Naureen and Sahiwal,
2013). From the very First time a person comes to a bank for depositing money, relation
beginsCustomer satisfaction is a person’s feeling of pleasure or disappointment resulting from
a product or service’s performance

in relation to his/her expectations (Akinyele et al., 2011). Lovelock and Wirtz (2005) pointed thatm
customer satisfaction is attitude like judgment following a purchase act or a series of customer

product interactions. Customers and even banks attach importanceto satisfaction (Amoah-Mensah,
2010). Customer satisfaction for service sector like banking can also be interpreted in two ways, as

a process and as an outcome.

Customer satisfaction in the context of credit risk management is a critical factor for financial
institutions. It involves how customers perceive the bank's or financial institution's handling of
credit risks, which includes loan approvals, interest rates, customer service during the lending
process, and the management of their financial information.
 Key Factors Influencing Castomers satisfaction

Transparency and Communication:

Clear and transparent communication regarding the terms and conditions of loans, interest rates, and
any risks involved is essential.Customers appreciate knowing exactly what they are committing to and
the potential risks associated with their credit decisions.

Efficient Processes :

The efficiency of the credit approval process can significantly impact customer satisfaction. Quick and
straightforward procedures with minimal bureaucratic hurdles enhance the customer experience.

Fairness and Equity:

Perceived fairness in the assessment of creditworthiness and the setting of loan terms plays a crucial
role. Customers want to feel that they are being treated fairly compared to others in similar situations.

Customer Service:

The quality of customer service during the credit risk management process affects satisfaction levels.
Helpful, knowledgeable, and responsive staff can mitigate frustration and enhance the overall
experience.

Risk-Based Pricing:

While risk-based pricing (adjusting interest rates based on the customer's credit risk) is a standard
practice, it needs to be implemented transparently. Customers should understand why they are being
charged a particular rate and how they can potentially improve their terms in the future.

Financial Education:

Providing customers with education about credit risk, including how it is assessed and managed, can
empower them and lead to higher satisfaction. Educated customers are more likely to appreciate the
nuances of credit risk management and feel confident in their financial decisions.
 Strategies to enhance Customer Satisfaction

Implementing User-Friendly Technologies:

Using digital platforms and mobile apps to streamline the credit application and management process
can enhance customer convenience and satisfaction.

Regular Feedback Mechanisms:

Conducting surveys and soliciting feedback from customers about their experiences can help identify
areas for improvement in the credit risk management process.

Continuous Improvement of Staff Training:

Ensuring that staff are well-trained in both customer service and the technical aspects of credit risk
management can improve interactions and outcomes for customers.

Customized Solutions:

Offering tailored credit solutions that meet the specific needs of individual customers can enhance
satisfaction by providing a more personalized experience.

Proactive Communication:

Keeping customers informed about the status of their applications and any changes in their credit
terms can build trust and reduce uncertainty.

In conclusion, customer satisfaction in credit risk management is influenced by various factors

including transparency, efficiency, fairness, customer service quality, and financial education.
Financial institutions that excel in these areas are likely to see higher levels of customer satisfaction,
which in turn can lead to greater customer loyalty and a stronger competitive position in the market

A graph has been depicted shows, the rate of customer satisfaction towards Credit Risk Management
 Different model of Credit Risk Management

Definition:

Financial institutions used credit risk analysis models to determine the probability of default of a
potential borrower. The models provide information on the level of a borrower’s credit risk at any
particular time. If the lender fails to detect the credit risk in advance, it exposes them to the risk of
default and loss of funds. Lenders rely on the validation provided by credit risk analysis models to
make key lending decisions on whether or not to extend credit to the borrower and the credit to be
charged. With the continuous evolution of technology, banks are continually researching and
developing effective ways of modeling credit risk. A growing number of financial institutions are
investing in new technologies and human resources to make it possible to create credit risk models
using machine learning languages, such as Python and other analytics-friendly languages. It ensures
that the models created produce data that are both accurate and scientific.

Factors Affecting Credit Risk Modeling

Probability of Default (POD):

The probability of default, sometimes abbreviated as POD, is the likelihood that a borrower will
default on their loan obligations. For individual borrowers, POD is based on a combination of two
factors, i.e., credit score and debt-to-income ratio.

The POD for corporate borrowers is obtained from credit rating agencies. If the lender determines
that a potential borrower demonstrates a lower probability of default, the loan will come with a low
interest rate and low or no down payment on the loan. The risk is partly managed by pledging
collateral against the loan.

Loss Given Default (LGD):

Loss given default (LGD) refers to the amount of loss that a lender will suffer in case a borrower
defaults on the loan. For example, assume that two borrowers, A and B, with the same debt-to-income
ratio and an identical credit score. Borrower A takes a loan of Rs.10,000 while B takes a loan of
Rs.200,000.

The two borrowers present with different credit profiles, and the lender stands to suffer a greater loss
when Borrower B defaults since the latter owes a larger amount. Although there is no standard
practice of calculating LGD, lenders consider an entire portfolio of loans to determine the total
exposure to loss.

Exposure at Default (EAD):

Exposure at Default (EAD) evaluates the amount of loss exposure that a lender is exposed to at any
particular time, and it is an indicator of the risk appetite of the lender. EAD is an important concept
that references both individual and corporate borrowers. It is calculated by multiplying each loan
obligation by a specific percentage that is adjusted based on the particulars of the loan.
 Different types of credit risk
Credit default risk:

Credit default risk occurs when the borrower is unable to pay the loan obligation in full or when the
borrower is already 90 days past the due date of the loan repayment. The credit default risk may
affect all credit-sensitive financial transactions such as loans, bonds, securities, and derivatives.

The level of default risk can change due to a broader economic change. It can also be due because of a
change in a borrower’s economic situation, such as increased competition or recession, which can
affect the company’s ability to set aside principal and interest payments on the loan.

Concentration risk :

Concentration risk is the level of risk that arises from exposure to a single counterparty or sector, and
it offers the potential to produce large amounts of losses that may threaten the lender’s core
operations. The risk results from the observation that more concentrated portfolios
lack diversification, and therefore, the returns on the underlying assets are more correlated.

For example, a corporate borrower who relies on one major buyer for its main products has a high
level of concentration risk and has the potential to incur a large amount of losses if the main buyer
stops buying their products.

Country risk:

Country risk is the risk that occurs when a country freezes foreign currency payments obligations,
resulting in a default on its obligations. The risk is associated with the country’s political instability
and macroeconomic performance, which may adversely affect the value of its assets or operating
profits. The changes in the business environment will affect all companies operating within a
particular country.In conclusion, effective credit risk management is crucial for financial institutions
to safeguard their assets and ensure long-term stability.By employing a combination of credit risk
assessment, mitigation, monitoring, and portfolio management strategies, institutions can better
predict and manage potential credit losses.

These strategies not only help in identifying high-risk borrowers but also provide mechanisms to
mitigate the impact of defaults. Continuous monitoring and proactive management of the credit
portfolio further enhance the institution's ability to adapt to changing market conditions and
economic environments. Ultimately, a robust credit risk management framework supports
sustainable growth and financial resilience.
Introduction to credit risk management process and techniques
This module introduces the key ideas for managing credit risk. Managing credit risk is a complex
multidimensional problem and as a result there are a number of different approaches in use, some of
which are quantitative while others involve qualitative judgements. Whatever the method used, the
key element is to understand the behaviour and predict the likelihood of particular credits defaulting
on their obligations. When the amount that can be lost from a default by a particular set of firms is the
same, a higher likelihood of loss is indicative of greater credit risk. In cases where the amount that can
be lost is different, we need to factor in not just the probability of default but also the expected loss
given default. Determining which counterparty may default is the art and science of credit risk
management. Different approaches use judgement, deterministic or relationship models, or make use
of statistical modelling in order to classify credit quality and predict likely default. Once the credit
evaluation process is complete, the amount ofrisk to be taken can then be determined.

A. To understand the nature of credit assessment problems --

I)Credit risk can be viewed as a decision problem .

II)The major problem in assessment is in classifying credit risk .

B.TO understand the different techniques used to evaluate credit risk, namely --

I)judgemental techniques. 

II)deterministic models.

III) Statistical model.

C. To be able to set up and undertake the credit review process 

D. To know the basic contents of a credit policy manual.

Judgemental Technique:
Credit risk management is a critical function in financial institutions, designed to mitigate the risk of
loss due to borrowers failing to meet their contractual obligations.One of the key methods used in
credit risk management is judgmental techniques. These techniques rely on the experience, intuition,
and expertise of credit analysts and loan officers to assess the creditworthiness of potential
borrowers. Here are some of the primary judgmental techniques used in credit risk management.

(I) Credit scoring : While often associated with quantitative methods, credit scoring can also
incorporate judgmental elements. Credit analysts might adjust scores based on their qualitative
assessment of factors not fully captured by numerical models, such as the applicant’s character or
business prospects.
(I) Interview based assessment: Personal interviews with applicants can provide deeper insights into
their creditworthiness. Experienced loan officers use these interviews to gauge an applicant’s honesty,
reliability, and overall financial situation, which might not be evident from documents alone.

(II) Historical performance analysis: Credit analysts review the historical performance of similar
loans or borrowers to inform their judgments about current applications. This involves looking at
default rates, recovery rates, and other performance metrics.

Benefits of judgemental technique:

I) Flexibility : Allows for the consideration of unique or unusual circumstances that quantitative
models might overlook.

II) Expertise utilization: Leverages the experience and intuition of seasoned credit professionals.

III) Holistic review: Provides a more comprehensive assessment by integrating qualitative factors
with quantitative data.

Challenges of Judgemental technique:

Subjectivity : Decisions can be influenced by personal biases or inconsistencies between different

credit officers.

Lack of stadardization: Can lead to variability in credit decisions, making it harder to ensure
uniformity.

Time consuming: More labor-intensive and time-consuming compared to automated scoring models.

In conclusion, judgmental techniques are an essential component of credit risk management,

complementing quantitative methods and providing a richer, more nuanced assessment of credit risk.
They allow financial institutions to make more informed decisions by considering a broader range of
factors and leveraging the expertise of experienced credit professionals.

Deterministic Model
Deterministic models of credit risk are structured, rule-based approaches that use specific, predefined
criteria and formulas to assess and manage credit risk. Unlike stochastic models, which incorporate
randomness and probabilities, deterministic models operate under the assumption that certain inputs
will always produce the same outputs. Here are some key deterministic models used in credit risk
management:

(I) Credit scoring model: Credit scoring models assign a numerical score to a borrower based on their
credit history and other financial factors. Common deterministic credit scoring models include :

FICO model : Utilizes a range of factors such as payment history, amount owed, length of credit history, types of
credit used, and new credit inquiries to generate a score between 300 and 850.

Vantage Score: Similar to FICO but uses different criteria and weightings, producing a score between 300 and
850.
(II) Moody’s KMV Model : The Moody’s KMV model (also known as the Expected Default Frequency
or EDF model) estimates the probability of default based on a firm’s asset value, volatility, and debt
structure.

(III) Finalcial Ratio Analysis : Financial ratio analysis involves calculating and analyzing key ratios
from a borrower’s financial statements to assess creditworthiness. Common ratios include :

Debt Equity ratio : Measures the company’s financial leverage.

Current Ratio : Assesses the company’s ability to pay short-term obligations.

Interest Coverage Ratio: Evaluates the company’s ability to pay interest on its debt.

(IV) Credit Migration Matrices : Credit migration matrices track the movement of borrowers between
different credit ratings over time. These matrices can be used deterministically to predict future
ratings based on historical data and transition probabilities.

(V) Risk Matrices Model : RiskMetrics, developed by J.P. Morgan, is a methodology for assessing
market risk but can also be adapted for credit risk. It uses Value-at-Risk (VaR) to determine the
potential loss in value of a portfolio over a specified period, given normal market conditions. Though
VaR itself can be stochastic, the parameters used in RiskMetrics are often deterministic.

(VI) CHS Model : The CHS model is used to assess the probability of corporate default. It includes
financial ratios and market-based variables such as volatility and stock returns. The model uses a
logistic regression framework but is deterministic in that it applies a specific formula to calculate
default probability.

Benefits of Deterministic model

Predictability : The same inputs will consistently yield the same outputs, making the models highly
predictable.

Transparency: The rules and criteria used in these models are clear and can be easily understood
and communicated.

Efficiency : These models can process large amounts of data quickly and consistently, making
them suitable for automated systems.
Challenges of Deterministic model:
Lack of flexibility : These models might not adapt well to changing market conditions or unique
borrower circumstances.

Oversimplification: By relying strictly on predefined criteria, deterministic models might overlook

important qualitative factors.

Data sentivity: The accuracy of deterministic models heavily depends on the quality and accuracy of
the input data.

In summary, deterministic models of credit risk provide a structured, consistent approach to

assessing credit risk, offering predictability and efficiency. However, they should often be used in
conjunction with other methods, including judgmental and stochastic models, to provide a more
comprehensive risk assessment.

Statistical model
Statistical models of credit risk management are quantitative methods that use statistical techniques
to assess the likelihood of a borrower defaulting on their obligations. These models analyze historical
data to identify patterns and relationships that can predict future credit risk. Here are some key
statistical models used in credit risk management :

Logistic Regression : Logistic regression is a widely used statistical method for binary classification
problems, such as predicting whether a borrower will default or not. The model estimates the
probability of default based on various predictor variables (e.g., income, credit history, loan amount).

Liner Discriminate Analysis (LDA): LDA is used to find a linear combination of features that best
separates two or more classes (e.g., defaulters vs. non-defaulters). It assumes that the predictor
variables follow a multivariate normal distribution with class-specific means and a common
covariance matrix.

Probit Model: Similar to logistic regression, the probit model is used for binary outcomes but
assumes a normal cumulative distribution function.
Survival Analysis: Survival analysis models the time until an event occurs, such as a default. It can
handle censored data (borrowers who have not defaulted by the end of the study period.

Neural Network: Neural networks are a type of machine learning model that can capture complex
non-linear relationships between input features and the probability of default. They consist of
multiple layers of interconnected nodes (neurons) that process input data and learn patterns through
training.

Decision trees and random forests : Decision trees split the data into subsets based on the most
significant predictors of default, creating a tree-like model of decisions. Random forests are an
ensemble method that constructs multiple decision trees and averages their predictions to improve
accuracy and reduce overfitting.

Support Vector machines(SVM) : SVM is a classification method that finds the optimal hyperplane
separating defaulters from non-defaulters in a high-dimensional space. It works well for both linear
and non-linear classification problems by using kernel functions.

K- Nearest neighbour : KNN is a non-parametric method that classifies a borrower based on the
majority class of the 𝑘k nearest neighbors in the feature space. It’s simple and intuitive but can be
computationally intensive with large datasets.

Benefits of statistical model

Predictive Accuracy: Can capture complex relationships and interactions between variables.

Scalability : Suitable for handling large datasets and multiple predictor variables.

Data driven : Rely on historical data, which can provide objective insights into credit risk.

Challenges of Statistical model

Data quality : Require high-quality data for accurate predictions. Poor data can lead to unreliable
models
Complexity: Some models, particularly machine learning methods, can be complex to implement
and interpret.

Overfitting : Risk of overfitting to historical data, which can reduce the model’s ability to generalize
to new data.

Statistical models are essential tools in credit risk management, offering sophisticated methods to
predict the likelihood of default based on historical data. These models enhance the ability of financial
institutions to make informed lending decisions, manage risk, and optimize their portfolios. However,
they must be used carefully, considering their limitations and the quality of the data they are based on.

Tools used for credit risk management in bank

Credit risk management in banks involves using various tools and techniques to assess, monitor, and
mitigate the risk of borrowers defaulting on their obligations. These tools combine quantitative and
qualitative approaches to provide a comprehensive view of credit risk. Here are some of the key tools
used in credit risk management in banks :

(1) Credit scoring system :

Credit scoring systems evaluate the creditworthiness of individual borrowers by assigning a score
based on their credit history, financial condition, and other relevant factors. Popular credit scoring
models include: 1. FICO Score 2. Vintage score

(2) Credit Rating Models :

Credit rating models assess the credit risk of corporate borrowers and sovereign entities. Agencies
like Moody’s, Standard & Poor’s, and Fitch Ratings provide credit ratings based on their analysis of
financial statements, economic conditions, and industry trends.

(3) Risk Based Pricing:

Risk-based pricing involves adjusting the interest rate and other loan terms based on the borrower’s
risk profile. Higher-risk borrowers may be charged higher interest rates to compensate for the
increased risk.

(4) Credit Portfolio Management software:

Credit portfolio management software helps banks manage their loan portfolios by providing tools for
risk assessment, monitoring, and reporting. Examples include:

1. Moody’s analytics riskorigins.

2. SAS credit scoring.

3. Finastra fusion credit risk management.

(5) Internal rating based approach :

Under the Basel II and III frameworks, banks can use the IRB approach to calculate their capital
requirements for credit risk. This approach allows banks to develop their own rating systems and use
them to estimate PD, LGD, and EAD.

These tools collectively help banks manage their credit risk by providing comprehensive assessments,
ongoing monitoring, and appropriate mitigation strategies to ensure financial stability and
compliance with regulatory standards.
Banks use a combination of these tools to effectively manage credit risk, ensuring they maintain a
healthy loan portfolio and comply with regulatory requirements. By leveraging both quantitative and
qualitative approaches, banks can better assess, monitor, and mitigate risks associate
With lending actovity.
Principles for the Assessment of Banks’ Management of Credit Risk

Some principals to be maintained for carring out credit risk management. Some key points have been
structured on the basis of principals.

I)Establishing an appropriatecredit risk environment

II) Operating under a sound credit granting process

III) Maintaining an appropriate credit administration, measurement and monitoring process.

IV) Establils over credit risk.

V) The role of supervisors.

I)Establishing an appropriate credit risk environment

Principle 1: The board of directors should have responsibility for approving and periodically (at least
annually) reviewing the credit risk strategy and significant credit risk policies of the bank. The
strategy should reflect the bank’s tolerance for risk and the level of profitability the bank expects to
achieve for incurring various credit risks

Principle 2: Senior management should have responsibility for implementing the credit risk strategy
approved by the board of directors and for developing policies and procedures for identifying,
measuring, monitoring and controlling credit risk. Such policies and procedures should address credit
risk in all of the bank’s activities and at both the individual credit and portfolio levels.

Principle 3: Banks should identify and manage credit risk inherent in all products and activities. Banks
should ensure that the risks of products and activities new to them are subject to adequate risk
management procedures and controls before being introduced or undertaken, and approved in
advance by the board of directors or its appropriate committee.
 II)Operating under a credit granting process

Principle 1: Banks must operate within sound, well-defined credit-granting criteria. These criteria
should include a clear indication of the bank’s target market and a thorough understanding of the
borrower or counterparty, as well as the purpose and structure of the credit, and its source of
repayment.

Principle 2: Banks should establish overall credit limits at the level of individual borrowers and
counterparties, and groups of connected counterparties that aggregate in a comparable and
meaningful manner different types of exposures, both in the banking and trading book and on and off
the balance sheet.

Principle 3: Banks should have a clearly-established process in place for approving new credits as well
as the amendment, renewal and re-financing of existing credits

Principle 4: All extensions of credit must be made on an arm’s-length basis. In particulars to related
companies and individuals must be authorised on an exception basis, monied with particular care
and other appropriate steps s taken tocontrol or mitigate the risks of non-arm’s length lending.

III) Maintaining an appropriate credit administration, measurement and monitoring process

Principle 1: Banks should have in place a system for the ongoing administration of their various
individual credits, including credit risk-bearing portfolios.

Principle 2: All extensions of credit must be made on an arm’s-length basis. In particulars to related
companies and individuals must be authorised on an exception basis, monied with particular care
and other appropriate steps s taken to control or mitigate the risks of non-arm’s length lending.

Principal 3: Banks must have in place a system for monitoring the condition of uding determining the
adequacy of provisions and reserves.

Principle 4: Banks are encouraged to develop and utilise an internal risk rating system in managing
credit risk. The rating system should be consistent with the nature, size and complexity of a bank’s
activities.
Principle 5: Banks must have information systems and analytical techniques that enable management
to measure the credit risk inherent in all on- and off-balance sheet activities. The management
information syst should provide adequate information on the composition of the credit portfolio,
including identification of any concentrations of risk.

IV)Ensuring adequate controls over credit risk

Principle 1: Banks must ensure that the credit-granting function is being properly managed and that
credit exposures are within levels consistent with prudential standards and internal limits. Banks
should establish and enforce internal controls and other practices to ensure that exceptions to
policies, procedures and limits are reported in a timely manner to the appropriate level of
management for action.

Principle 2:Banks must have a system in place for early remedial action on deteriorating credits,
managing problem credits and similar workout situations.

Principle 14: Banks must establish a system of independent, ongoing assessment of the bank’s credit
risk management processes and the results of such reviews should be communicated directly to the
board of directors and senior management.

V)The role of supervisor

Principle 1: Supervisors should require that banks have an effective system in place to identify,
measurehe role of supervisors monitor and control credit risk as part of an overall approach to risk
management. Supervisors should conduct an independent evaluation of a bank’s strategies, policies,
procedures and practices related to the granting of credit and the ongoing management of the
portfolio. Supervisors should consider setting prudential limits to restrict bank exposures to single
borrowers or groups of connected counterparties.

Most major banking problems have been either explicitly or indirectly caused by weaknesses in credit
risk management.Severe credit losses in a banking system usually reflect simultaneous problems in
several areas, such as concentrations, failures of due diligence and inadequate monitoring. This
appendix summarises some of the most common problems related to the broad areas of
concentrations, credit processing, and market- and liquidity-sensitive credit exposures.
Case Study