I am working on a project to develop a system that detect credit card fraud. I have no data set to test my system on instead I want to create a database that looks similar to that of a real bank database.

Are there some samples out there? I mean one that would show some columns to include? Of course, I know it depends on the requirements of my system but, what have you done - that is what I want to see.

I know some would have worked on similar situations. What have you included?

PS: I know (from SO) that credit card information must not be stored without authorization or some policies out there BUT this is specifically for demonstrating my system, just demonstration!

1 Answer 1


Datasets like this will typically be "academic", meaning scrubbed and anonymized and used for demo or publishing purposes.

One example is the "German Credit fraud data", which is in ARFF format as used by Weka machine learning.

This dataset classifies people described by a set of attributes as good or bad credit risks. Comes in two formats (one all numeric). Also comes with a cost matrix.

As far as I can tell, this data is the story of 1000 credit lines and not specifically credit cards.

One useful thing may be to reverse search who is using this dataset, namely who links to it.

(my source)

Other possibilities:

This file concerns credit card applications. All attribute names and values have been changed to meaningless symbols to protect confidentiality of the data.

This dataset is interesting because there is a good mix of attributes -- continuous, nominal with small numbers of values, and nominal with larger numbers of values. There are also a few missing values.

  • Well, thanks for edit and response, this has provided me with a start. I am looking into it.
    – CN1002
    Oct 18, 2015 at 12:17

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.