Loan Data Analysis and Approval Prediction System For

LOAN DATA ANALYSIS AND APPROVAL
PREDICTION SYSTEM FOR CUSTOMERS
• Submitted by:- • Submitted to:-

• Abhay Vaish • Mrs. Alka Singh
• CS41,1750810002 • Assistant Professor
• BBDEC • CSE Dept.,BBDEC
TABLE OF CONTENT
• INTRODUCTION • RESULTS
• PROBLEM STATEMENT • LIMITATIONS AND ADVANTAGES
• PROPOSED SOLUTION • FUTURE SCOPE
• MODULES • REFERENCES
• FEASIBILITY STUDY
• HARDWARE REQUIREMENT
• SOFTWARE REQUIREMENT
• TECHNOLOGIES USED
• TABLES
• UML DIAGRAM-USE CASE
• SCREENSHOTS
INTRODUCTION
• The project “Loan data analysis and approval prediction system” includes gathering data
from many years of loan applications,
• The software has the ability to learn from the bulk of data that is given to it and find patterns
in the data to group similarities and find anomalies . It uses robust and latest machine
learning algorithms to analyse the data and find missing data as well as data the is not in
standard terms.
• It uses many techniques to study the data and has the ability to visualise data using different
graphs and in 3 dimensions as well.
• It asks for very few details from the customer such as name ,marital status, gender,
dependents, employment status ,extra income, yearly income ,loan period, last loan status.
• With few parameters it uses latest python libraries and accurate machine learning algorithms
to show the status of loan approval and if approved then the amount offered by the Bank.
PROBLEM STATEMENT
In todays world the economy is the sole driving factor of mankind. For a better
lifestyle people come up with new ideas to generate revenue but with the ever
increasing prices and population on the planet , every individual faces
challenges and pressure on resources is very high.
Thus to fuel the ideas of future so that sustainable development of mankind
continues and no great ideas go in trash money is the biggest factor .Banks and
loans pay a vital role in present day economy. They help every individual
realise their dreams by providing loans.
To process thousands of applications and bulk of information available in the
digital era poses the greatest challenges of the late 21st century.
PROPOSED SOLUTION
To fast forward the application process and to assist bank employees as well as
the customers it is very important to maintain an error free , easily accessible
transparent system. The processing of previous data is the most cumbersome
and tedious process and also to avoid any missing data there is an dire need of
robust and simple yet powerful system that could do the work of months in few
hours, increasing the speed and efficiency of the economy.
Our project aims to develop a system that could deploy the power of the
emerging field of artificial intelligence and machine learning to quickly absorb
all available data and process it to show the patterns ,graphs , predictions ,
trends to better understand customer requirements and reduce HUMAN
HOURS by 80 to 90 percent.
MODULES
GUI: the interface uses pythons “Tkinter” module to design the interface. Tkinter is used to design
input bars and buttons and backgrounds.
ScikitLearn: Scikit-learn is a free machine learning library for Python. It features various
algorithms like support vector machine, random forests, and k- neighbours, and it also
supports Python numerical and scientific libraries like NumPy and SciPy
NumPy: It is used to deal with matrices, linear algebra, matrix transformations.
Pandas: It is a high-level data manipulation tool developed by Wes McKinney. Its key data structure
is DataFrames used to manipulate Tabular data.
PyMySql: PyMySQL is an interface for connecting to a MySQL database server
from Python. It implements the Python Database API v2. 0 and contains a pure-Python
MySQL client library. The goal of PyMySQL is to be a drop-in replacement for MySQLdb..
Matplotlib: Matplotlib is a plotting library for the Python programming language and its
numerical mathematics extension NumPy.
FEASIBILITY STUDY
An important outcome of the preliminary investigation is the determination
that Loan Data Analysis and Approval System is feasible or not. In the conduct
of feasibility-study, there are three major interrelated areas which are to be
taken in consideration . They areas follows :
Technical Feasibility : To develop this application , a database server and a
software is required . The current project is feasible because it is deployed on
Jupyter Notebook , Python Language and a browser(chrome).
Operational Feasibility : We need the database maintenance cost. This is the
basic operational cost which tend to be very low.
Economical Feasibility : The application is free to install once released in
market.
HARDWARE REQUIREMENTS
This system doesn’t require any hardware interface . The one used here is monitor,
keyboard and mouse. The system should have these hardware requirements:
Processor – 64 bit distribution capable of running 32 bit applications.
Keyboard – 104 keys
RAM – 3 GB minimum, 8 GB RAM recommended.
Monitor – 14’’ VGA COLOR
Mouse – Logitech Serial Mouse
Memory – 512 GB or above
Hard Disk – 10 GB or above.
Disk Space – 2 GB of available disk space minimum.
SOFTWARE REQUIREMENTS
Tools Used :
NumPy
Pandas
Matplotlib
Front End Tools :
Tkinter
Back End Tools :
PyMySQL
Jupyter Notebook
TECHNOLOGIES REQUIRED
PYTHON :- Python is a general purpose and high level programming language. We canuse Python
for developing desktop GUI applications, websites and web applications. Also,Python, as a HLL,
allows you to focus on core functionality of the application by taking care of common programming
tasks. The simple syntax rules of the programming language further makes it easier for us to keep
the code base readable and application maintainable. The syntax rules of Python allow you to
express concepts without writing additional code.
MACHINE LEARNING :- Machine learning is an application of artificial intelligence (AI) that
provides systems the ability to automatically learn and improve from experience without being
explicitly programmed. Machine learning focuses on the development of computer programs that
can access data and use it learn for themselves. The process of learning begins with observations or
data, such as examples, direct experience, or instruction, in order to look for patterns in data and
make better decisions in the future based on the examples that we provide. The primary aim is to
allow the computers learn automatically without human intervention or assistance and adjust actions
accordingly.
TABLES:
• Initial Data:
• Converted training data:
• Converted Testing Data:

Entity-Relationship Diagram:
SCREENSHOTS:
RESULT:
• “Loan Data Analysis and Approval System” is very efficient
,reliable and economic software and different modules can be
added in future to scale up the software.
• The project is in its starting stage and has huge scope of
upgrade.
• It significantly reduces Human Hours and Human labour in
analysis and approval of applications.
• The customers can rely on it as it uses latest technologies such
as python , machine learning , Tkinter etc.
• The software is very advantageous as it provides fastest
prediction and a graphical representation of the data fed to the
system.
• It is free open source hence it is easily accessible and very
simple to use.
Limitations:
• Very few features
• Very simple interface
• Less modules
• Requires an internet connection to send mails
Advantages:
• It can send mail on user mail id if loan is approved
• Tells user about the amount allotted to him/her.
• If not whole the a part amount is also suggested by the system base on user
data.
Future scope:
• Many more modules can be added
• The software can be hosted online for wide
community to use
• Sms facility could be added
• More features could be added to training data
to make the prediction more real-life
• It can add real time facility
THANK YOU!

Loan Data Analysis and Approval Prediction System For

Uploaded by

Copyright:

Available Formats

Loan Data Analysis and Approval Prediction System For

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Loan Data Analysis and Approval Prediction System For

Uploaded by

Copyright:

Available Formats

LOAN DATA ANALYSIS AND APPROVAL

PREDICTION SYSTEM FOR CUSTOMERS

• Submitted by:- • Submitted to:-

• Converted training data:

• Converted Testing Data:

You might also like