/German_Credit

An EDA of the German Credit Dataset on Kaggle

Primary LanguageJupyter Notebook

German_Credit

Data Source

This is the exploratory data analysis of the German Credit Database.

This dataset is a subset of the full dataset by Prof. Hofmann. Original dataset: UCI

Data Description

In this dataset, each entry represents a person who takes a credit by a bank. There are 1000 such entries and 9 features.

Project Goal

To do Exploratory Data Analysis of this dataset and find interesting insights.

Code click here

Conclusion

  • As credit amount went up duration for the credit also went up

credit_heatmap

  • People didn't prefer to take big credits for large amount of time

credit_dur_regplot

  • We can see that highly skilled workers took greater credit amount than others even though they applied for less no. of applications

Job_num_application Job_amount

  • The biggest applications for credit were for car. People with free housing where applying to get cars.

Purpose_count

No. of applications by people with free housing according to purpose of application:

free_purpose

Social Preview Photo Credit:

Photo by Josh Appel on Unsplash