search

AI4Risk / antifraud

A repository for financial fraud detection
GNU General Public License v3.0
174 stars 43 forks source link

Clarification on Dataset Fields in FFSD Compared to Described in the Paper #8

Closed a245589351 closed 11 months ago

a245589351 commented 11 months ago

Hello,

I am currently reviewing your work on the FFSD dataset. In your paper, it was mentioned that the attributes of the card include the card type, cardholder type, card limit, remaining limit, etc. The transaction attributes include the channel ID, currency ID, transaction amount, etc. The merchant attributes contain merchant type, terminal type, merchant location, sector, charge ratio, etc.

However, when observing the dataset in the source code, I only see the following fields: Time, Source, Target, Amount, Location, Type, Labels.

Could you kindly clarify the correlation between the fields in the source code dataset and those described in the paper? Additionally, I would appreciate if you could provide a brief explanation for what each field in the source code dataset represents.

Thank you for your time and I look forward to your response.

Best regards,

wei4zheng commented 11 months ago

Hello, may I ask where you are or if there is a paper for this code? I couldn't find a paper for "rgtan." Could you please provide information about it? Thank you very much.

a245589351 commented 11 months ago

Hello,

The paper associated with this code is titled "Semi-supervised Credit Card Fraud Detection via Attribute-driven Graph Representation", which was published in AAAI 2023.

I couldn't find any descriptions related to rgtan in the paper.

Best regards,

bingreeky commented 11 months ago

Thanks for reaching out.

  1. For FFSD dataset, please note that the S-FFSD provided in this repo is a condensed version of FFSD, and we cannot release the full version due to restrictions imposed by our data source partners, regretfully.
  2. RGTAN is our work in progress which has not been published yet. We will provide further details upon acceptance of the paper or its submission to arXiv.
a245589351 commented 11 months ago

Thank you for your response.

I understand the constraints regarding the full version of the FFSD dataset and I appreciate your efforts in providing the condensed version. To clarify, I am specifically interested in understanding the complete structure of the FFSD dataset, not the actual data itself. Having this information would be extremely beneficial for my understanding of your work and would allow me to better comprehend the nuances of the paper.

Also, I'm looking forward to learning more about your ongoing work on RGTAN once it's published or submitted to arXiv. Your research is of great interest to me and I'm excited to see your future contributions.

Thank you again for your time and consideration.