Department of Electronicsand Computer Science Engineering
Shree L. R. Tiwari College of Engineering
Kanakia Park, Mira Road (E), Mumbai-401107
UNIVERSITY OF MUMBAI
2023-2024
Bachelor of Engineering
Project Presentation
2.
A PRESENTATION ON
“CreditRisk Analysis”
By
HARSH DUBEY-12
ANIKET SHUKLA-44
MANAS VESVIKAR-54
Under the guidance of
PROF. SAMITA BHANDARI
3.
Introduction
• Credit riskis associated with the possibility of a client failing to meet
contractual obligations such as mortgages, credit card debts, and other
types of loans.
• Minimizing the risk of default is a major concern for many
organizations and financial institutions.
• For this reason, commercial and business bank venture capital funds,
asset management companies, and insurance firms are increasingly
relying on technology to predict which clients are more prone to stop
honoring their debts.
• Machine learning models can be used to help these companies improve
the accuracy of their credit risk analysis, providing a scientific method
to identify potential debtors in advance.
4.
Problem Statement
Despite itssignificance, the credit risk analysis system has several issues. They
majorly include availibility of quality data and suitable tools for credit scoring and
vetting. These problems are a big part of financial operations and need to be
watched carefully. Managing and countering these problems is very essential to
keep the financial system stable. Data quality and accessibility, global
intercorrectness, regulatory adherence, rise of non-traditional lenders, economic
volatility and human factors are some of the biggest challenges faced by the credit
risk analysis system.
5.
Abstract
• Risk analysisis a crucial component of any project.
• Problems can arise in the financial sector as well.
• Credit risk is a potential financial loss resulting from a counterparty’s
breach of contract or increased risk of default during course of
transaction.
• The objective is to implement machine learning applications in order
to detect loan defaulters.
6.
Literature Survey
SR NO.NAME OF AUTHOR YEAR TITLE OF PAPER
1 Sudhamathy G. 2016 Credit Risk Analysis and
Prediction Modelling of bank
loans.
2 Jonathan N. Crook/
David B. Edelman/
Lyn C. Thomas
2007 Recent developments in
consumer credit risk
assesments.
3 Aida Krichene
Abdelmoula
2015 Bank credit risk analysis with K-
nearnest neighbour classifier :
Case of Tunisian Banks.
4 Martin Leo, Suneel
Sharma, K. Maduletty
2019 Machine Learning in Banking
Risk Management : A literature
review.
Framework Requirements
• PYTHON
Pythonis a popular general-purpose programming language. It is used in machine learning, web
development, desktop applications, and many other fields. Fortunately for beginners, Python
has a simple, easy-to-use syntax.
• STREAMLIT
Streamlit is an open-source Python library that provides developers with an easy and efficient
way to build attractive user interfaces. It is particularly useful for those with no front-end
knowledge, as it eliminates the need for HTML, JS, or CSS experience. With Streamlit,
developers can quickly turn their code into a fully functional web application, without the
hassle of front-end development.
10.
Machine Learning AlgorithmsRequired
• K Neighbours: K-neighbour is a type of supervised learning algorithm used for both
classification and regression.
• SVC: SVC is a specific implementation of the Support Vector Machine algorithm that is
designed specifically for classification tasks.
• Decision Trees: Decision trees are non-parametric supervised learning methods used for
classification and regression.
• Gaussian Naive Bayes: Gaussian NB is a machine-learning classification technique
based on a probabilistic approach that assumes each class follows a normal distribution.
• Linear Discrimination Analysis: LDA is a statistical technique for classifying data into
groups. It identifies patterns in features to distinguish between different classes.
• Logistic Regression: Logistic Regression is a classification technique that identifies the
best-fitting model to describe the relations between the dependent and independent
variables in a dataset.
• Random Forest: Random Forest or Random decision forest is an ensemble learning
method for classification, regression, and other tasks that operates by constructing a
multitude of decision trees at training time.