Loan Eligibility Prediction

System
Submitted in the partial fulfillment for the award of
the degree of
BACHELOR OF ENGINEERING
IN
Information Security
Submitted by: Under the Supervision of:
Aananaya Mathur SUPERVISOR’S NAME:
Asmita Bharti Professor Nirmalya Basu
Soham Mukherjee
Abhishek

Department of AIT-CSE DISCOVER . LEARN . EMPOWER

2
Introduction to Project
• The main business of practically all banks is the distribution of loans. The
main portion the bank's assets directly comes from the profit earned from
the loans distributed by the banks. In a banking environment, the main
goal is to place one's assets in trustworthy hands.
• Today, many banks and financial institutions grant loans through a lengthy
verification and validation process, but there is still no assurance that the
chosen applicant is the most deserving candidate among all applicants.
• With the help of this system, we can determine whether a specific
application is secure or not, and the entire feature validation procedure is
automated using machine learning technology.

3
PROBLEM FORMULATION
• The banks nowadays not only provide their services in urban but in rural
areas also. The banking system is growing fast and is dealing with
millions of people all the time. Customers applies for a loan by filling
out numerous forms and going to and fro to the emloyees to validate
their status of eligibility.
• The eligibility of a customer can be determined the details they provide
about their age, marital status, salary, FDs, RDs, etc. The system
requires a real time process for improving the efficiency and latency
caused due to human errors.
• Here, we provide a system to automate the process by bringing every
aspect of loan eligibility under one roof.
4
OBJECTIVES
GOALS

Qualified customers could

System identifies
Automate (real-time) customer segments
qualification process with
almost no error percentage.

5
Methodology used
• The project makes use of pandas, matplotlib and seaborn libraries from
python to extract insights from the data and xgboost and scikit learn
libraries for machine learning
• We train our model to predict the eligibility with cross validation.
• The model uses two main functions
•We have existing data, it reads from csv file and trains the system, then
predict the loan eligibility
•Graph is plotted with factors including applicant income, loan duration,
etc
•Based on training the eligibility is predicted for all applicants
•The AUC score is also generated for two time verification
6
Methodology used
• The output generated consist of the loan ID and the eligibility status
• If we need a system to predict for a single aspirant
• Manual input is taken for different attributes
• To predict whether the loan applicant can repay the loan or not we
use voting ensembling technique.
• Complexity of the technique is low whereas accuracy is high.

7
Results and Outputs

8
Results and Outputs

9
Results and Outputs

10
Results and Outputs

11
Results and Outputs

12
Results and Outputs

13
Results and Outputs

14
Results and Outputs (GUI)

15
Results and Outputs

16
Results and Outputs

17
Results and Outputs

18
Results and Outputs

19
Results and Outputs

20
Conclusion
• In this project, machine learning approach to predict loan eligibility
and their credit worthiness. We employed different machine learning
algorithms on the dataset in order to determine which algorithms are
best by using voting ensembling technique.
• The project revealed that the algorithms such as xgboost, adaboost,
forest, and decision tree perform credibly well in term of their
accuracy and other performance evaluation matrices.

21
Future Scope
• Future studies should include more such independent variables to be
able to derive a more detailed perspective of the analysis and gain
more insight into the process.
• We also need to perform demographic analysis to identify obligors
and understand the nature of scope transactions so we can identify
and trigger them early in the future.

22
Few References
• https://
www.hdfcbank.com/personal/borrow/popular-loans/personal-loan/el
igibility
• https://
www.researchgate.net/publication/357449126_THE_LOAN_PREDICTI
ON_USING_MACHINE_LEARNING
• https://www.youtube.com/results?search_query=loan+eligibility
• https://
towardsdatascience.com/predict-loan-eligibility-using-machine-learni
ng-models-7a14ef904057

23