Link to web app: https://nullfraudfraudclassifier-gziclh2a9gk.streamlit.app/
generated from streamlit/Interactive-Data-Explorer
-
Notifications
You must be signed in to change notification settings - Fork 0
Developed a Random Forest classifier to predict fraudulent transactions for a hackathon, employing extensive exploratory data analysis to uncover critical insights into feature impacts on fraud likelihood. Worked with an imbalanced dataset with only 0.2% minority class, applied techniques like SMOTE to balance data, achieving highest F1-score.
nazifishrak/nullfraud-fraud-classifier
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Developed a Random Forest classifier to predict fraudulent transactions for a hackathon, employing extensive exploratory data analysis to uncover critical insights into feature impacts on fraud likelihood. Worked with an imbalanced dataset with only 0.2% minority class, applied techniques like SMOTE to balance data, achieving highest F1-score.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published