Recap

Fraud Detection in Python

Charlotte Werger

Data Scientist

Working with imbalanced data

• Worked with highly imbalanced fraud data
• Learned how to resample your data
• Learned about different resampling methods

Fraud detection with labeled data

• Refreshed supervised learning techniques to detect fraud
• Learned how to get reliable performance metrics and worked with the precision recall trade-off
• Explored how to optimize your model parameters to handle fraud data
• Applied ensemble methods to fraud detection

Fraud detection without labels

• Learned about the importance of segmentation
• Refreshed your knowledge on clustering methods
• Learned how to detect fraud using outliers and small clusters with K-means clustering
• Applied a DB-scan clustering model for fraud detection

Text mining for fraud detection

• Know how to augment fraud detection analysis with text mining techniques
• Applied word searches to flag use of certain words, and learned how to apply topic modeling for fraud detection
• Learned how to effectively clean messy text data

Further learning for fraud detection

• Network analysis to detect fraud
• Different supervised and unsupervised learning techniques (e.g. Neural Networks)
• Working with very large data

End of this course

Fraud Detection in Python