Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 29

Predict Loan Eligibility using

Machine Learning Models


Overview
 Introduction
 Objectives
 Methodology
 Data
 Exploratory Data Analysis (EDA)
 Machine learning Techniques
 Logistic Regression
 Decision Tree
 Support Vector
 Naive Bayes
 Confusion Matrix
 Results
 Conclusion
 References
Introduction
 Extending credits to corporate and individuals for the
smooth functioning of growing economies like India is
inevitable.
 There is an increasing number of customers apply for

loans in the banks


 There should be safe procedure to lend money to its

borrowers for their financial needs.


 There are may techniques to predict loan eligibility

using Machine learning models


Objectives

 To determine whether there is a chance for non


repayment
 To determine best and accurate method to predict

eligibility for loan


Methodology
 Data collection
 Data cleaning and processing
 Applying the model for prediction
 Determining the accuracy followed by confusion

matrix
Data
 The feature in the dataset includes:
1. Loan_Id
2. Gender
3. Marital Status
4. Number of dependents
5. Educational Profile
6. Employment Status
7. Applicant‘s Income
8. Co-Applicant‘s Income
9. Loan Amount
10. Loan Tenure
11. Credit History
12. Property Area
13. Loan Status
Data cleaning and processing

 Fill the missing values with mean values regarding


numerical values.
 Fill the missing values with mode values regarding

categorical variables.
 Outlier treatment.
Exploratory Data Analysis (EDA)
Applying the model for prediction

 Create the target variable


 Create a dummy variable for categorical variable and

split the training and testing data for validation.


 Apply the model
Machine learning Techniques
 Logistic Regression
 Decision Tree
 Support Vector
 Naive Bayes
Logistic Regression
 In general, linear Regression model was used to predict
the functionalities of a continuous variables
 If the variable is categorical, instead of continuous,

then the LR method is adopted.


 The output of LR model is dichotomous i.e., binary

possibilities, used for prediction of loan sanction


possibilities.
Logistic Regression
Decision Tree
 In decision analysis, a decision tree can be used to
visually and explicitly represent decisions and decision
making.
 As the name goes, it uses a tree-like model of

decisions.
 It is a commonly used tool in data mining for deriving

a strategy to reach a particular goal


Decision Tree
Support Vector
 SVM or Support Vector Machine is a linear model for
classification and regression problems.
 It can solve linear and non-linear problems and work

well for many practical problems.


 The idea of SVM is simple: The algorithm creates a

line or a hyperplane which separates the data into


classes.
Support Vector
Naive Bayes
 Naive Bayes is the most straightforward and fast
classification algorithm, which is suitable for a large
chunk of data.
 Naive Bayes classifier is successfully used in various

applications such as spam filtering, text classification,


sentiment analysis, and recommender systems.
 It uses Bayes theorem of probability for prediction of

unknown class.
Naive Bayes
Confusion Matrix
 A Confusion matrix is an N x N matrix used for evaluating the
performance of a classification model, where N is the number
of target classes.
 The matrix compares the actual target values with those
predicted by the machine learning model.
 This gives us a holistic view of how well our classification
model is performing and what kinds of errors it is making.
Confusion Matrix

Predicted values
Negative (0) Positive (1)
Actual Values

Negative (0) TN FP
Positive (1) FN TP
Results

Parameters Loan prediction model


LR DT SVM NB

Loan Prediction 0.8285 0.8265 0.775 0.8345


Accuracy
Results
Conclusion
 Machine learning techniques revels the capability of
the borrower to repay the loan and thus they reduce the
risk of the bank
 All the machine learning techniques are providing

more than 60% accuracy


 The most accurate method for loan prediction is Naive

Bayes
References
 Loan approval prediction using KNN, decision Tree
and Naïve Bayes models , IJECS 2020; Volume 2 Issue
1: page no 32-37
 Loan Prediction by using Machine Learning Models

International Journal of Engineering and Techniques -


Volume 5 Issue 2, Mar-Apr 2019
 Loan Prediction Dataset Source,

https://www.kaggle.com/panamby/bank-loan-status-
dataset/data

You might also like