Banking Credit Card Spend Prediction

credit card prediction

Idea and Concept:  

Credit scores are designed to make decisions easier for lenders. The bank would like to understand what factors are driving credit card spend. The bank wants to use these insights to calculate credit limit. Credit scores help lenders decide whether or not to approve loan applications and determine what loan terms to offer. The scores are generated by algorithms using information from the credit reports, which summarize the borrowing history of a customer.  

Objective and approach:  

The objective of our project is to understand what’s driving the total spend (Primary Card + Secondary card). Given the factors, predict credit limit for the new applicants. Dataset available was in xlsx format. The data have been provided for 5000 customers. Detailed data dictionary has been provided for understanding the data in the data. Data is encoded in the numerical format to reduce the size of the data however some of the variables are categorical. You can find the details in the data dictionary.  


In general, the collected data was for 5000 customers and we wished to understand what is driving the total spends of credit card and prioritize the drivers based on the importance. The cloud platform used for the project is GCP. So, after acquiring the data, it was ingested to Google cloud storage and AI platform notebooks were used for the deployment of models. This process included intensive data cleaning or preparation, generating correlation matrix, performing factor analysis; filtering variables using correlation as well as Linear Regression modelling. Finally, we built data visualizations on Power BI.  


Following are a few conclusions corresponding to the columns.  

lncreddebt : log of credit card debt in thousands. If user has more debt on credit card, then his credit card limit is more and the user is likely to have more income. If user has more debt on credit card, then she/he spends more with credit card and haven’t repaid.  

carcatvalue: Primary vehicle price category. Person owning economic car likely to have less credit card spend as she/he would prefer more on saving and likely to defer from buying expensive items.  

debtinc : If debt to income ratio is high, person is likely to spend less. 

Contact Our Cloud Experts

Get Free Consultation
Share on facebook
Share on twitter
Share on linkedin
Share on pinterest
Share on whatsapp
Share on email

Leave a Reply

Your email address will not be published. Required fields are marked *

Recent Post

Hadoop Vs. Hbase

Hadoop is an open-source framework of programs that is used to store and process big data. Hadoop uses multiple clusters of computers to analyze big data sets in parallel. The distributed processing of data sets can

Read More »
no sql databases

No SQL Databases : Types

No SQL databases are non-relational databases. It is an approach to database design which allows storage and retrieval of data in a non-tabular format as that found in relational database. NoSQL

Read More »

Contact us for a quote, help, or to join the team.



(732) 347-6245

About Us

iSmile Technologies is a global technology services company.
(732) 347-6245


+1 (732) 347-6245
241 Jonathan Way
Bolingbrook, IL 60490


2-3-285, Secunderabad Hyderabad 500003


3190 Stocksbridge Ave
Oakville, ON L6M 0A7