I’ve just completed my final project and am looking forward to hearing some feedback on it. I did have to trim the dataset down to get it fitting in my github: Portfolio/Online Payment Fraud Detection.ipynb at 0e934683ad9d8094098977cb0a596af2b350f6ce · kittela/Portfolio · GitHub
To summarize, it was a dataset I pulled from Kaggle which contains payment transactions identified as fraudulent and non-fraudulent. I threw a few classification models at it and ultimately found Random Forest to work the best by a long shot. One thing in particular I’d like to ask for a double-check on is that the Decision Tree and Logistic Regression models are showing the same recall score. Not sure if I messed something up along the way but I’m having trouble figuring that one out.
Thanks for reading!