In the realm of banking, gaining insights into potential defaulters for the Consumer Loans product is crucial for informed decision-making. This report aims to explore valuable insights derived from probability and hypothesis testing within a dataset that encompasses variables such as age, income, marital status, experience, city, profession, and risk flag (indicating loan default occurrences). By analyzing these factors, our objective is to predict who possible defaulters are for the consumer loans product.
Dataset : https://www.kaggle.com/datasets/subhamjain/loan-prediction-based-on-customer-behavior
In this analysis, some data will be used as listed in the following table.
However, I did not use all of them, after going through the cleaning process, I decided to use the data on income, age, experience, profession, married, house & car ownership, city, and risk flag.
- How is the proportion and distribution based on its default loan?
- How are the proportion between variables with default loans?
- How is the correlation between variables?
- How is the decision that we got from this analysis?
youtube link : https://youtu.be/SuKIUBMPaNQ
report link : https://medium.com/@wtaufikbudi/bank-loan-based-on-customer-behaviour-67af5a4ad678