LOAN APPROVAL PREDICTION USING

MACHINE LEARNING

GUIDED BY:
M. Krishna Kishore

PRESENTED BY:
Keerthi Nallamalla 2011CS010191
Manju Tanguturi 2011CS010192
Praneetha Nekkanti 2011CS010193
Sindhuja Nune 2011CS010199

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

MALLA REDDY UNIVERSITY
 ABSTRACT

 The loan is one of the most important products of the banking. All the banks are trying to figure
out effective business strategies to persuade customers to apply their loans. However, there are
some customers behave negatively after their application are approved.

 In today’s world there are many risks involved in bank loans, so as to reduce their capital loss;
banks should perform the risk and assessment analysis of the individual before sanctioning loan. In
the absence of this process there are many chances that this loan may turn in to bad loan in near
future. Banks hold huge volumes of customer behavior related data from which they are unable to
arrive at a decision point i.e. if an applicant can be defaulter or not.
PROBLEM DEFINITION

 The loan defaulter prediction is a binary classification problem Loan amount, costumer’s history
governs his credit ability for receiving loan.

 The problem is to classify borrower as defaulter or non-defaulter. Prototypes can be used by the
organizations for making the correct or right decision for approve or reject the request for loan of
the customers.

 The result of this credit risk assessment will be the prediction of probability of Default of an
applicant.

 Python Package is an excellent statistical tool that can handle any volume of structured as well as
unstructured data and provide the results in a fast manner and presents.
 SCOPE OF PROJECT

What is loan default?

 A loan default or loan delinquency is your failure to make loan re-payments when they are due.

 Extended delinquency can result in a loan default.

 It is the failure to repay the loan as per the terms agreed between you and the bank.

 In case of a secured loan, a home or a car can be absorbed and sold by a credit institution.

 For a non secured loan i.e. a personal loan, your credit score is likely to get damaged and the bank

is liable to take legal action against you .

NEED FOR PREDICTING LOAN DEFAULTS
 Not surprisingly, defaulting on a loan comes with consequences. The specifics depend on your situation, but you
can usually count on damage to your
credit and additional expenses:
 Credit and legal troubles:
 Your credit will suffer when you fail to make your required payments.
 For the first 30 days after payment is due, you’re probably in the clear.
 After that, lenders report missed payments to credit bureaus, resulting in lower credit scores.
 Lower scores make it hard to get loans in the future, and low credit score can impact several other areas of your life.
High expenses:
 To make matters worse, your financial burden will probably grow if you default on a loan.
 Late payment fees, penalties, and legal costs might be added to your account , increasing the total balance you owe.
 DESCRIPTION

What is python?

 Python is a popular programming language. It was created in 1991 by Guido van Rossum. Python is a high-level,
general-purpose programming language. Its design philosophy emphasizes code readability with the use of significant
indentation.

 including structured (particularly procedural), object-oriented and It is used for :

Web development (server-side) , Software development, Mathematics, System scripting.

Why Python?

 Python works on different platforms (Windows, Mac, Linux, etc.).

 Python has syntax that allows developers to write programs with fewer lines than some other programming languages.

 Python runs on an interpreter system, meaning that code can be executed as soon as it is written. This means that
prototyping can be very quick.
TECHNOLOGY USED
This project will be a Web-based application to be developed using Python
Hardware requirement:
 64-bit operating system of windows, Linux, etc.
 8GB RAM Minimum (16GB Preferred).
 intel i5 3200k and above with more than 2.6GHz
Software Requirement:
 Programming language: Python3.7
 Machine learning Library: scikit-learn (0.19.1)
 Python packages: pandas(0.20.0) for data processing,
 NumPy(1.14.3) for data manipulation,
 Matplotlib (2.2.2) for visualization
 IDE: Anaconda 5.3.0, jupyter notebook, Flask
 Database: Dataset (.csv format file)
LOGISTIC REGRESSION
 Logistic regression is a supervised learning classification algorithm used to predict the probability
of a target variable. The nature of target or dependent variable is dichotomous, which means there
would be only two possible classes.

Advantages:

 Logistic Regression performs well when the dataset is linearly separable.

 Logistic regression is less prone to over-fitting but it can overfit in high dimensional datasets. You
should consider Regularization (L1 and L2) techniques to avoid over-fitting in these scenarios.

 Logistic Regression not only gives a measure of how relevant a predictor (coefficient size) is, but
also its direction of association (positive or negative).

 Logistic regression is easier to implement, interpret and very efficient to train. 

IMPLEMENTATION
PREDICTION MODELING

The steps involved in model building methodology are represented as below:

 Data Selection
 Data Pre-Processing
Outlier Detection
Splitting, Training & Test Datasets
Balancing Training Dataset
 Features Selection
Correlation Analysis of Features
 Building Classification Model
 Predicting Class Labels of Test Dataset
 Evaluating Predictions
THANK YOU