Predict Credit Card Fraud
A demo on constructing a model designed to detect credit card fraud.
Billions of dollars are lost annually to credit card fraud in the United States. While the majority of credit card transactions are legitimate, detecting fraudulent transactions using traditional methods is challenging. Machine learning, particularly no-code machine learning technology like Akkio, can efficiently detect and prevent credit card fraud by identifying patterns in historical data and creating predictive models. Akkio's no-code machine learning technology allows for the fast and easy development and deployment of fraud detection models, enabling the timely warning of customers about potentially fraudulent transactions.
This file has nearly 285,000 rows of real credit card transactions from the EU. Because this credit card information is sensitive, the information in each one of the columns has been encoded using a mechanism called principal component analysis, or PCA.
There are 28 different pieces of information that come along with each credit card transaction, along with the size of the transaction, in Euros, and finally whether or not that transaction was fraud. That final column is what we’re trying to predict.
Last updated