In this data analysis exercise, our team has come up with a solution to address business intelligence questions that arose from the Credit Card Data set that we obtained from Kaggle. A relevant paper on the same data set is present here. We have used IBM SPSS Modeller to achieve the same. The Output Analysis streams and Images can be found in their respective folders.
This dataset contains information on default payments, demographic factors, credit data, history of payment, and bill statements of credit card clients in Taiwan from April 2005 to September 2005. There are 24 attributes and 30000 instances (records).
A few important questions that we intend to answer from this dataset include:
- Does demographics play a role in credit card customers defaulting?
- In terms of classification, which are the variables that the split commonly happens in?
- Which variables are the strongest in terms of prediction of default payment?
- Decision Tree
- K-means clustering
- Support Vector Machines
- Artificial Neural Networks
- Regression