fbpx

Code: EDI-2019-18-YKT

Domain: Finance

Summary

Forecasting fraud transactions of credit card users of YKT with machine learning technics instead of traditional rule-based systems.

Proposed by

 

Yapı Kredi Teknoloji is a Turkish company that delivers outputs in machine learning, data mining, pattern recognition, artificial intelligence and natural language processing fields and develops mobile applications.

Description

Existing fraud prevention mechanism in banks are mostly based on manpower-based rules. These rules evaluate the fraud risk of credit card transactions and inform the fraud operation team according to the risk scores of rules. This process is daily reported to the credit cardholders by operation team by considering the daily call capacity. This challenge is about forecasting fraud transactions of credit card users of YKT with machine learning technics instead of traditional rule-based systems. Credit card fraud means a transaction that is not intentionally performed by the card holder.

Data

The challenge has the following sample datasets available for download

Expected outcomes

Detection Rate (DR) and False Positive Rate (FPR) are the indicators for success criteria:

  • DR is the percentage of correctly detected fraudulent credit card transactions.
    Detection Rate = DR = (# of detected fraudulent credit cards / # of fraudulent credit cards)
  • FRP, on a transaction basis, shows the ratio of fraudulent transactions detected by the developed model to the total number of fraudulently predicted transactions.
    False Positive Ration = (FPR) = (# of legitimate credit cards detected as fraudulent / # of detected fraudulent cards)

So, the expected outcomes are:

  • Detection Rate = (>50%), roughly 50% of all true credit card fraud transactions
    should get caught.
  • False Positive Rate = (30/1) According to this rate, if there is 30 fraudulent credit
    card transaction predicted, one of them is true fraudulent.

The typical evaluation metrics of a machine learning system should also be provided. Also, Confusion matrix of all fraud-nonfraud transactions to observe FN, FP, TP, TN.
These are the metrics for fraud and non-fraud transactions:

  • FN: False Negative
  • FP: False Positive
  • TP: True Positive
  • TN: True Negative

How do we apply?

Follow by Email
Facebook
Twitter
YouTube
SOCIALICON