A PROJECT REPORT

OF THE COURSE

Machine Learning [INT 214]

ON THE TOPIC OF

CREDIT CARD
APPROVAL PREDICTION

PROGRAMME NAME: Bachelor of Technology

(Computer Science and Engineering)

Under the guidance of Dr. Dhanpratap Singh

SUBMITTED BY
HARI PRASAD BODDEPALLI 12112271
AYUSH GUPTA 12105138
ABHINANDHAN 12108947

I
 DECLERATION
I hereby declare that the project work entitled “Credit card Approval Prediction” is an authentic
record of my own work carried out as requirements of Project for the award of B. Tech degree in
Computer Science and Engineering from Lovely Professional University, Phagwara, under the
guidance of Dr Dhanpratap Singh, during August to December 2023. All the information furnished
in this project report is based on my own intensive work and is genuine

2th November 2023

HARI PRASAD BODDEPALLI 12112271

AYUSH GUPTA 12105138

ABHINANDHAN 12108947

CERTIFICATE
This is to certify that the declaration statement made by this student is correct to the best of my
knowledge and belief. He has completed this Project under my guidance and Supervision. The
present work is the result of his original investigation, effort and study. No part of the work has
ever been submitted for any other degree at any University. The Project is fit for the submission
and partial fulfilment of the conditions for the award of B. Tech degree in Computer Science and
Engineering from Lovely Professional University, Phagwara.

Dr Dhanpratap Singh

School of Computer Science and Engineering,

Lovely Professional University,

Phagwara, Punjab

Date: 2th November, 2023

II | Page
 TABLE OF CONTENTS
1. Introduction
2. What is Credit Card?
3. Credit Card Scoring and Decisioning Models
4. Effects of ML credit card customer experience
5. Comparison of different supervised machine
learning classifiers to predict credit card
approvals
6. Predicting credit card approval of customers
through customer profiling using machine
learning
7. Advantages of a credit card
8. Disadvantages of a credit card
9. Challenges of credit card approval using
machine learning
10. Model generation
11. Conclusion and future scope
12. References

III
 INTRODUCTION
Credit approval, such as for credit cards, is crucial to the
modern economy. In today's interconnected global economy,
credit approval, such as for credit cards, plays a pivotal role.
Even in developing nations like India, the accessibility of credit
cards has become a reality. However, for financial institutions,
the challenge lies in accurately assessing whether a consumer
represents an acceptable credit risk for granting credit. This
challenge is particularly pronounced in emerging economies,
where conventional rules and models from more developed
nations may not be directly applicable.
In this report, we present our investigation into the prediction
of credit card approval for applicants using various machine
learning algorithms. Our research journey begins with data
preprocessing and comprehensive exploratory data
analysis(EDA) to gain deeper insights into the critical factors
influencing the model's training. Subsequently, we apply ten
distinct machine learning algorithms to the preprocessed data,
aiming to identify the model that strikes the optimal balance
between accuracy and precision-recall trade-off.
The report is structured as follows: In Section II, we share the
insights derived from our literature review, shedding light on
the existing knowledge in this domain. In Section III, we provide
a detailed exposition of our entire system, covering data
preprocessing, model selection, and evaluation. We also
present and analyze the results obtained, comparing them from
different perspectives. Finally, in the concluding section, we
summarize our findings and observations.

IV | Page
 WHAT IS A CREDIT CARD?

Credit cards are offered by banks and NBFCs (Non-Banking

Financial Company) to carry out seamless, cashless transactions
online and offline. The credit card lender sets a pre-decided
limit on your credit card based on your income, credit score
and other factors. You can use the credit card for various
transactions up to the maximum credit limit. The credit card bill
is regenerated at a regular interval. If you pay the bill within the
due date, interest will not be imposed. However, after this
period, the bank will charge a certain interest rate.

V
 CREDIT SCORING AND
DECISIONING MODELS
Credit Scoring

Credit scoring is a statistical analysis performed by financial lenders

to determine the creditworthiness of an individual or a business. This
creditworthiness is influenced by several key factors:

1. Credit History: The primary source of information is usually the

applicant’s credit history, which is a detailed record of all past
borrowing and repayment, including late payments and defaults.
Credit bureaus compile this data and generate credit reports.
2. Personal Information: Personal data, such as income level,
employment status, and length of credit history, are vital pieces of
information. This information is often self-reported by the applicants
on their credit application.
3. Other Data Sources: In recent years, alternative data has become
increasingly important. This could include utility bills, rent payments,
bank account information, and even social media activity. All these
sources provide a more holistic view of the applicant’s financial
behavior.

VI | Page
Based on these data points, models generate a credit score. This credit
score is then used to decide whether to extend credit to a borrower
and at what interest rate. Credit scores typically range from 300 to
850, with higher scores indicating less risk to the lender.

Credit Decisioning

Credit decisioning, on the other hand, is the process by which

financial institutions make decisions on credit applications. It involves
evaluating the borrower’s creditworthiness and the likely profitability
of the loan to the lender. This margin may differ based on the firm’s
risk appetite and lending strategy.

For example, a lender specializing in subprime loans might accept

higher default probabilities than a traditional bank. Additionally,
firms must comply with federal and state financial regulations.

VII
In another example, lenders cannot discriminate based on age, race,
religion, nationality, or marital status, and such factors must be
handled appropriately by the model. Ultimately, the decisioning
process may result in acceptance, rejection, or a request for additional
information.

EFFECTS OF ML CREDIT CARD

CUSTOMER EXPERIENCE
Machine learning and artificial intelligence are leading a new
digitisation renaissance across multiple global industries. In the
financial landscape, machine learning and AI are not new
technologies. Banks, financial institutions, and more have relied on
machine learning algorithms for critical processes. But now more and
more banks are moving towards utilising the emerging prowess of
newer machine learning models towards the credit card industry.

ML is perfect for the credit card industry as the technology can help
companies make sense of humongous sets of data and give insights
about every single customer within the ecosystem. From bolstering
fraud detection to fine-tuning personalized financial trajectories, this
cutting-edge technology is orchestrating a paradigm shift in financial
services.

VIII | Page
Machine learning operates as a type of artificial intelligence, enabling
computers to learn like humans do, by building on past experiences.
It's like teaching a computer to recognize patterns in information
without much human help. This technology delves into data, finding
patterns on its own, and doesn't need constant human guidance.

Any task that follows certain patterns or rules from data can be
automated using machine learning. This means things like handling
customer calls, managing accounts, or even going through resumes
can be done by machines. Machine learning systems tackle large
amounts of data, finding important patterns within it.

IX
COMPARISON OF DIFFERENT
SUPERVISED MACHINE
LEARNING CLASSIFIERS TO
PREDICT CREDIT CARD
APPROVALS :-
This study contrasts various supervised machine learning models to
forecast the likelihood that a credit card request will be accepted
based on various criteria like Precision, Recall, Time, Accuracy, and
F1 Score. The aim here was to identify the best classifier for
automatically predicting credit card approval based on the
characteristics of credit card applications. The analysis also
demonstrates that every classifier performs better in one or more
metrics. To improve the performance of each model, the method used
hyperparameter optimization based on GridSearchCV to optimise
certain parameters. The UCI Machine Learning Repository dataset
used in this work was unbalanced and hence F1 score was relied on
up to test the models. The classifiers used in this study are Logistic
Regression, Random Forest, Decision Tree, XGBoost, Gradient
Boost, Support Vector Machine (SVM), and Sequential Neural
Network. Finally, based on F1 Score and AUC value, the research

X | Page
finds that Random Forest classifier is the best model for predicting
Credit Card approvals with a F1 score of 86%. Although the research
tries multiple machine learning models to test the dataset, there was
no attempt made to balance out the data for better results.

PREDICTING CREDIT CARD

APPROVAL OF CUSTOMERS
THROUGH CUSTOMER
PROFILING USING MACHINE
LEARNING
This study focuses on forecasting credit card approval for users using
a limited number of algorithms. The data was taken from bank
customers in 2 ways, primary data and secondary data and then
combined into one. These customer datasets were fully gathered,
evaluated, and trained. These trained datasets helped in predicting
whether credit card applications from customers will be approved.
Since only a small number of variables were employed to determine
the final decision, the training and testing accuracy of both decision
tree and k nearest neighbour algorithms were roughly 99.7% and
99.6%, respectively. The training and testing accuracies of the
decision and knn algorithms would alter in real time as more datasets
are trained and tested and as the variables for the final choice are

XI
raised. This study however falls short in testing various other
classification algorithms that could show better results in the future
when more variables are taken in consideration.

ADVANTAGES OF A
CREDIT CARD
A credit card has several benefits with thw help of ml as well . They
are as follows:

1. EMI Option :
Credit cards are excellent for purchasing goods and services with a
low monthly EMI. This alleviates the burden of having to pay the
money in one lump sum. Furthermore, EMI payments via credit cards
may be more convenient than obtaining a personal loan.

2. Exciting Offers and Cashbacks :

Most banks offer credit cards with a variety of offers, cashbacks, and
rewards. These offers and rewards are available whenever you make
an online or offline purchase. You can also get cheaper air tickets,
train tickets, hotel reservations, grocery shopping, and so on.

XII | Page
3. Protection of Purchase :
Credit cards provide extra security in the form of insurance for card
purchases that are lost, damaged, or stolen. If you want to file a claim,
you can use the credit card statement to back it up.

4. Improving Credit Score :

Credit cards allow you to build up a credit line. This is critical
because it allows banks to view an active credit history based on your
card repayments and card usage. Banks and financial institutions
frequently use credit card usage to assess a potential loan applicant’s
creditworthiness, making your credit card important for future loan or
rental applications.

5. Enhanced Accuracy:

Machine learning algorithms have the ability to analyze vast amounts

of data and identify patterns that may not be apparent to human
analysts. By incorporating various data points, including credit
history, income, employment, and spending patterns, machine
learning models can make more accurate predictions regarding an
individual's creditworthiness. This leads to better-informed credit card
approval decisions, reducing the risk of defaults and improving
overall portfolio performance.

6. Faster Processing:

XIII
Traditional credit card approval processes can be time-consuming,
involving manual reviews, paperwork, and extensive documentation.
Machine learning streamlines this process by automating many of the
tasks. By leveraging algorithms and predictive models, financial
institutions can expedite credit card approvals, providing customers
with faster access to credit facilities.

7.Personalized Offerings:

Machine learning enables lenders to personalize credit card offerings

based on individual profiles and preferences. By analyzing customer
data and behavior, machine learning algorithms can identify specific
needs, spending patterns, and risk profiles. This allows lenders to
tailor credit card features, such as interest rates, credit limits, rewards
programs, and promotional offers, to match the unique requirements
of each customer.

8.Risk Mitigation:

The use of machine learning algorithms in credit card approval helps

mitigate risks associated with lending. By accurately assessing
creditworthiness and identifying high-risk applicants, financial
institutions can make informed decisions on interest rates, credit
limits, and terms of repayment. This not only protects lenders from
potential losses but also ensures responsible lending practices and
safeguards the financial well-being of customers.

XIV | Page
 DISADVANTAGES OF A
CREDIT CARD :-
Here are a few disadvantages of using a Credit Card:
1. Hidden Costs :-
Credit cards may appear easy and straightforward initially, but
they comprise numerous hidden costs that can increase the
expense amount by a high margin. These extra charges can
come in the form of late payment costs, renewal fees,
processing fees etc. Nevertheless, if you miss any payment, it
can cause a penalty and diminish your credit history.
2. Restricted Drawings :-
Credit cards, unlike debit cards, do not offer as many benefits
when it comes to cash withdrawals. This is due to the fact that
some credit cards charge an additional fee in addition to an
annual interest rate of approximately 40%.

CHALLENGES OF CREDIT
CARD APPROVAL USING
MACHINE LEARNING
1. Data Privacy and Security: The use of machine learning in
credit card approval requires access to vast amounts of

XV
sensitive customer data. It is crucial for financial institutions to
implement robust data privacy and security measures to protect
this information from unauthorized access or misuse. Strict
compliance with data protection regulations and encryption
techniques is essential to ensure the confidentiality and
integrity of customer data.
2. Model Interpretability and Transparency: Machine learning
algorithms can be complex, making it challenging to interpret
and explain the decisions they make. This lack of interpretability
can pose challenges in terms of regulatory compliance and
consumer trust. Efforts must be made to develop transparent
models that provide clear explanations for credit card approval
decisions, ensuring fairness and accountability.
3. Bias and Fairness: Machine learning algorithms are
susceptible to bias as they learn from historical data that may
contain inherent biases. This can lead to discriminatory
practices in credit card approval, impacting certain
demographic groups unfairly. It is important to continuously
monitor and evaluate machine learning models to ensure
fairness and mitigate any bias that may arise.

XVI | Page
 MODEL GENERATION
Step 1: Loading datasets
The code begins by importing essential libraries for data
manipulation, visualization, and machine learning. These
libraries include Pandas (pd), NumPy (np), Seaborn (sns),
Matplotlib (plt), and specific modules from scikit-learn. The
primary goal is to load and process two datasets:
"application_record.csv" and "credit_record.csv."

Step 2: Merging datasets

In this step, the two datasets are combined into a single DataFrame
(data) using the Pandas merge function. The merging is based on the
'ID' column, which is assumed to be a common identifier in both
datasets. This merging allows us to have a comprehensive dataset
containing both application details and credit records.

Step 3: Exploring the data

1. *Basic Statistics*: The code uses the data.describe() function to
compute and display basic statistics for the dataset. This
includes statistics such as mean, standard deviation, minimum,
maximum, and quartiles for numeric columns. It gives an
overview of the data's central tendencies.
2. *First Few Rows*: The data.head() function is used to display
the first few rows of the merged dataset. This is useful for
understanding the structure and contents of the data.

XVII
Step 4: Data Cleaning
Data cleaning is a crucial step to ensure the quality and integrity of
the dataset:
- *Missing Values Check*: The code uses data.isnull().sum() to
count and display missing values in each column. This is
important for identifying columns with missing data.
- *Removing Rows with Missing Target Variable*: Rows with
missing values in the 'STATUS' column are removed using
data.dropna(subset=['STATUS']). This is done to ensure that
only records with credit status information are retained for the
modeling process.

Step 5: Defining features

A set of features that will be used as input for the machine learning
model is defined. These features represent various attributes and
characteristics related to the applicants, such as gender, income,
education, and more. These features are stored in the 'features' list.

Step 6: Selecting features and target

variable
In this step, the code selects the independent variables (features) and
the dependent variable (target) to prepare the data for modeling:
- X contains the selected features from the dataset.
- y contains the target variable, which is 'STATUS,' representing the
credit status.

XVIII | Page
Step 7: Converting categorical variables
to numerical using one-hot encoding
Many machine learning algorithms require numerical input, so
categorical variables need to be converted into a numerical format.
One-hot encoding is used for this purpose. It creates binary columns
for each category within the categorical variables, indicating the
presence or absence of each category.

Step 8: Data Visualization

Data visualization is an essential part of data exploration. The code
plots a histogram of income distribution using Seaborn and
Matplotlib. This visualization provides insights into the distribution of
income levels in the dataset.

Step 9: Splitting the data into training

and testing sets
To assess the model's performance, the dataset is divided into training
and testing subsets. The train_test_split function from scikit-learn is
used for this purpose. It allocates 80% of the data for training (X_train
and y_train) and 20% for testing (X_test and y_test).

Step 10: Initializing and training the

Random Forest Classifier
A Random Forest Classifier is initialized with 100 decision trees. It is
a machine learning model used for classification tasks. The model is

XIX
then trained on the training data (X_train and y_train) to learn patterns
and relationships within the data.

Step 11: Making predictions on the test

set
The trained Random Forest Classifier is used to make predictions on
the test set (X_test). The predicted values are stored in the 'y_pred'
variable.

Step 12: Evaluating the model using

classification report
To assess the model's performance, a classification report is generated
using the classification_report function from scikit-learn. This report
includes various metrics such as precision, recall, F1-score, and
support for each class, allowing a detailed assessment of the model's
ability to classify different credit statuses.

Step 13: Displaying the classification

report
Finally, the classification report is displayed, providing a
comprehensive summary of the model's performance. It includes
accuracy and other classification metrics for different credit statuses,
helping to evaluate the model's effectiveness in predicting credit
outcomes.
This code represents a complete machine learning workflow, from
data preprocessing to model evaluation, in the context of predicting
credit statuses based on applicant and credit record data.

XX | Page
 FUTURE SCOPE
To further improve our system, we can use deep learning models as it
can increase our accuracy. Neural networks can be used as it can
discover hidden patterns and correlations in raw data, cluster and
classify it, and continuously learn and improve over time. In the
future, this credit card approval system will be able to be optimized
and implemented in an artificial intelligence environment. By
displaying the prediction result on a web or desktop application, the
system can also be automated. Thus, this work has a good future
scope and can be enhanced by adding other various feature for better
predictions.

CONCLUSION
In this paper, we have mentioned various machine learning methods
to predict whether a credit card will be approved for an individual or
not. Several parameters were taken into consideration as these
parameters make the model more effective and help institutions make
better decisions to avoid fraud and losses. We applied a lot of data
pre-processing techniques as good amount of data pre-processing
contributes effectively to developing better performance of traditional
machine learning models. During Exploratory Data Analysis, we
plotted a lot of graphs and charts to study the dataset deeply so that
we can get a better understanding of the dataset. This was done so that
we can decide which models to apply which can perform well on this
dataset and can correctly predict whether to approve a credit card or
not. This prediction system can be helpful to various banks as it
makes their task easier and increases efficiency as compared to the
manual system which is currently used by many banks and this
system is cost effective.

XXI
 REFERENCES
• www.google.com
• www.wikipedia.com
• www.ijraset.com
• https://github.com/AyushGupta16/Credit-Card-
Approval-Prediction.git

XXII | Page