Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 14

REVIEW 1

LITERATURE SURVEY

ACCESSING CREDIT RATING AND CREDIT


RISK IN BANKING DOMAIN USING
MACHINE LEARNING APPLICATIONS

Name : Saravana Kumar T


Reg no : 23MCA1108
Faculty name : A.B Ahadit
Faculty Id : 53164
ABSTRACT

• In the financial domain, credit rating associated with loan applicants


is essential for processing loans.
• Machine learning application is used in assessing and quantifying the
credit risk associated with loan applicants.
• Automation powered by machine learning applications reduces
processing times and operational costs.
• The other important benefits of using machine learning applications
are the elimination of human bias and improving user experience by
providing faster response.
INTRODUCTION

• The critical process in the financial industry is loan approval, where


the lending institution accesses the creditworthiness of the applicants
before approving loans
• Assessing loan applications manually can be time-consuming and
there is a chance for errors.
• Machine learning techniques offer a data-driven approach to
automate and enhance the loan approval process.
MOTIVATION

• The banking industry is becoming data-centric because it generating


vast amounts of customer information.
• Traditional credit rating methods often fail to capture the full details
of a borrower's creditworthiness.
• Machine learning application enables banks to leverage this data for
more accurate credit scoring and risk evaluation.
• Improved credit rating and risk management can lead to reduced
default rates, increased profitability, and enhanced customer
satisfaction.
PA P ER 1 : I N T E LLI G E N T LO A N ELI G I BI L I TY A N D A P P RO VA L S Y S T EM BA S E D O N
RA N D O M FO RE ST A L G O RI T H M U S I N G M A CH I N E L EA RN I N G . [ 1 ]

Author C.Prasanth, R.Praveen Kumar, Dhiyanesh B, B.Rangesh, N.Sasmitha

Year of
publish 2023, International Conference on Innovative Data Communication Technologies and Application
And (ICIDCA)
publisher

Algorithm Random Forest Algorithm, Decision Tree


Metrics
Module Precision, Recall, Error Rate and Accuracy
used
Accuracy 89%

Dataset used Dataset used in this paper is called “Loan Prediction” and no detail about where the data is taken

No of
13 features
features

List of Loan_Id , Gender, Married, Dependents, Education, Self_Employed, ApplicantIncome,


features CoApplicantIncome, LoanAmout, Loan_Amount_Term, Credit_History, Property_Area, Loan_status
PA P ER 2 : PR ED I CT I N G L O A N A P PR O VA L O F BA N K D I RE CT MA RK ETI N G D ATA
U S I N G EN S EMBL E MA CH I N E L EA R N I N G A L G O R I T H MS . [ 2 ]

Author Hossam Meshref

Year of
publish
2020, International Journal of Circuits, Systems and Signal Processing
And
publisher
Algorithm Bagging, Boosting, Random Forest Algorithm, decision tree
Metrics
Accuracy, Precision, Recall, F1 score
used
Accuracy 89%

Dataset used Dataset used in this paper is called “loan prediction” and no detail about where the data is taken

No of
8 features
features
List of
mentioned age, job, marital, education, default, balance, housing, loan
features
PA P ER 3 : H Y BR I D ML C LA SS I F I E R FO R LO A N PR ED I CT I O N S Y S TE M .[ 3 ]

Author Kavitha M, Saranya S, Dhinesh, Sabarish, Gokulkrishnan A

Year of
publish and 2023, International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)
publisher

Algorithm Hybrid model of Naïve Bayes and Decision Tree

Metrics
Recall, Sensitivity, F-measure, Accuracy, and Precision
used

Accuracy 84%.

Dataset used Dataset used in this paper is called “loan application” and it is taken from Kaggle.

No of
13 features
features
List of
mentioned The list of features is not mentioned.
features
PA P ER 4 : P RE D I C TI O N O F L O A N S TATU S I N CO M M E RCI A L BA N K U S I N G M A CH I N E
LE A R N I N G C LA S S I F I E R. [ 4 ]

Author G. Arutjothi, Dr. C. Senthamarai

Year of
publish and 2017, International Conference on Intelligent Sustainable Systems (ICISS)
publisher

Algorithm k-Nearest Neighbor classifier and Min-Max normalization

Metrics
Accuracy, RMSE, Correlation, Error Rate
used

Accuracy 84%.

Dataset used Retrieved from a publicly available data set of lending club repository loan data

No of
74 features
features
List of
The list of features is not mentioned
features
PA P ER 5 : A ZU REML BA SE D A N A LY SI S A N D P R ED I CT I O N L O A N BO RRO W E RS
CR ED I TW O RT H Y. [ 5 ]

Author Khaldoon Alshouiliy, Ali AlGhamdi, Dharma P Agrawal

Year of
publish
2020, International Conference on Information and Computer Technologies (ICICT)
And
publisher

Algorithm Two Class Decision Jungle and Two Class Boosted Decision Tree

Metrics
Precision, Accuracy, Recall,F1 Score and AUC
used

Accuracy 75.08%

Dataset used Dataset used is LendingClub dataset

No of
20 features
features
List of
type_of_loan,Type_of_home_ownership,Loan_status,Individual_terms
features
PA P ER 6 : P RE D I C TI O N O F M O D ER N I Z ED L O A N A P PRO VA L S Y S TE M B A S ED O N
M A CH I N E L EA RN I N G A P P RO A CH . [ 6 ]

Author Vishal Singh, Ayushman Yadav, Rajat Awasthi, N.Partheeban

Year of
publish
2021, International Conference on Intelligent Technologies (CONIT)
And
publisher

Algorithm XG boost, random forest and decision tree


Metrics
No metric usage is mentioned in this paper
used
Accuracy 77%

Dataset used “historical data of candidate” but they not mentioned where they collect data

No of
13 features
features

List of Loan_id, Gender, Marries, Dependents, Education, Self_Employes, Applicant_Income,


features Co_Applicant_Income, Loan_Amount, Loan_Amount_term, Credit_history, Property_area, Loan_status
PA P ER 7 : A N A P P RO A CH FO R PR ED I CT I O N O F LO A N A P P RO VA L U S I N G M A C H I N E
LE A R N I N G A LG O R I TH M. [ 7 ]

Author Mohammad Ahmad Sheikh , Amit Kumar Goel, Tapas Kumar

Year of
publish
2020, International Conference on Electronics and Sustainable Communication Systems (ICESC)
And
publisher

Algorithm Logistic Regression


Metrics
confusion matrix, Accuracy, precision, Recall, F1 score
used
Accuracy 81%

Dataset used The dataset is collected from the kaggle

No of
13 features
features
sex, married, no_dependents, in_service, self_employed, annual_income_coapplicant,
List of
annual_income_applicant, amount_loan, credit_history_applicant, loan_amount_ transfer, assests,
features
loan_amount_log
FUTURE WORK

• To create a Machine learning model to improve model accuracy.

• To improve the accuracy of the model.

• Exploratory data analysis of banking-related features.

• Comparison of existing machine learning algorithm and choose


append algorithm.
• [1] C.Prasanth, R.Praveen Kumar, Dhiyanesh B, B.Rangesh, N.Sasmitha , “Intelligent Loan Eligibility and Approval System based on
Random Forest Algorithm using Machine Learning”, International Conference on Innovative Data Communication Technologies and
Application (ICIDCA).
• [2] Hossam Meshref, “Predicting loan approval of bank direct marketing data using ensemble machine learning algorithms”, International
Journal of Circuits, Systems and Signal Processing.
• [3] Kavitha M, Saranya S, Dhinesh, Sabarish, Gokulkrishnan A, “Hybrid ML Classifier for Loan Prediction System”, International
Conference on Sustainable Computing and Data Communication Systems (ICSCDS).
• [4] G. Arutjothi, Dr. C. Senthamara, “Prediction of Loan Status in Commercial Bankusing Machine Learning Classifier”, International
Conference on Intelligent Sustainable Systems (ICISS)
• [5] Khaldoon Alshouiliy, Ali AlGhamdi, Dharma P Agrawal, “A Z U R E M L B A S E D A N A LY S I S A N D P R E D I C T I O N L O A N
B O R R O W E R S C R E D I T W O RT H Y ” , International Conference on Information and Computer Technologies (ICICT).
• [6] Vishal Singh, Ayushman Yadav, Rajat Awasthi, N.Partheeban, “P R E D I C T I O N O F M O D E R N I Z E D L O A N A P P R O VA L
S Y S T E M B A S E D O N M A C H I N E L E A R N I N G A P P R O A C H ” , International Conference on Intelligent Technologies
(CONIT).
• [7] Mohammad Ahmad Sheikh , Amit Kumar Goel, Tapas Kumar, “A N A P P R O A C H F O R P R E D I C T I O N O F L O A N
A P P R O VA L U S I N G M A C H I N E L E A R N I N G A L G O R I T H M ” , International Conference on Electronics and Sustainable
Communication Systems (ICESC).

You might also like