Train and deploy your XGBoost model in Amazon SageMaker

Photo by NASA on Unsplash

We will use a Kaggle dataset about credit card fraud detection. This dataset consists of transactions made by credit cards in September 2013 by European cardholders. It contains 492 frauds out of a total of 284,807 transactions. You can see that it is highly unbalanced, where the positive class (frauds) account for 0.172% of all transactions.
The objective of this article is to illustrate how…