Data Set - Loan Default Dataset - https://www.kaggle.com/datasets/yasserh/loan-default-dataset

Questions???

What best combination of categories can be used to predict defaulting successfully?

• Testing SVM and using Permutation feature importance to understand what features are most important to predicting defaulting
• Testing decision trees with different k parameters

Can you predict interest rates based on social factors (gender, religion, age)? Do these higher interest rates lead to higher default rates? Does this suggest a level of discrimination that occurs when banks give out loans?

• kNN decision tree of gender versus interest rate
• SVM of social factors

What variables are most important in having a high loan payout?

• Variables plan to use: Gender, lona-type, loan_purpose, credit worthiness, credit open, property value, construction type, term, occupancy_type, secured_by, credit type, credit score, dtir1, income, security type, region, age, co-applicant credit type to predict to predict loan_amount

Methods

• Using linear model, lasso, and ridge

Code To Read Data

!pip install kagglehub

import kagglehub

import pandas as pd

path = kagglehub.dataset_download("yasserh/loan-default-dataset")

dataset_path = f"{path}/Loan_Default.csv"

data = pd.read_csv(dataset_path)