Fraud Detection on Financial Transactions with Machine Learning on Google Cloud

This self-paced lab on Google Cloud explores financial transactions data for fraud analysis. Participants will learn to load data into BigQuery, apply feature engineering, and utilize machine learning techniques to detect fraudulent activities.

Key learning points include:

• Exploring and creating new features in BigQuery
• Building an unsupervised model for anomaly detection
• Constructing supervised models for fraud detection using logistic regression and boosted tree
• Evaluating and comparing models to select the champion for predicting the likelihood of fraud on test data