The aim of the tutorial is to explore and understand payment transactions data. Particularly, it is of interest to build ML models to classify fraudulent transactions.

You will learn the following areas:

• Conducting exploratory data anlysis (EDA),
• Handling personally identifiable information (PII),
• Inspecting data leakage,
• Perfoming feature engineering,
• Dealing with class imbalance,
• Modeling building, and diagnostics
  • Logistic regression,
  • Naive Bayes classification,
  • k-NN,
  • SVM.
• Model evaluation and interpretation
  • Confusion matrix,
  • Performance metrics,
  • ROC-AUC.