Loan-Approval

The aim is to identify the customer segments to whon the loan can be granted. The main objective is to analyze and predict whether assiging the loan to a particular person will be safe or not based on specific features.

Data Source : Kaggle.com

Python Libraries used

1. Pandas
2. NumPy
3. Matplotib
4. Seaborn
5. from sklearn.model_selection import train_test_split
6. from sklearn.neighbors import KNeighborsClassifier
7. from sklearn import tree
8. from sklearn.metrics import accuracy_score
9. from sklearn import metrics
10. from sklearn.metrics import classification_report, confusion_matrix

Pre-processing operations

1. Checking for missing values
2. Filling missing values
3. Checking for duplicate values
4. Removing certain columns
5. Converting certaon objects
6. Checking for outliers/extreme values

Exploratory Data Analysis

1. Gender obtaining maximum number of loans
2. Effect of marital status on the target value
3. Effect of education on the target value
4. Effect of employment on the target value
5. Effect of credit history on the target value
6. People of which area obtain more number of loans
7. Target variable analysis
8. Applicant income distribution
9. CoApplicant income distribution
10. Loan amount distribution
11. Correlation between the variables

Model Building

Implemented supervised learning algorithm that follows non-parametric apporach

KNN

Decision Tree