This repository contains the procedure we followed.
Since the data for credit card fraud is not available in real form(due to confidentiality), and is availbale only in dimensionality reduced form, we will be sharing some of the test cases here.
-
Architecture
- Logistic Regression with balanced class weight.
-
Inference Results
- Accuracy: 0.976
- Recall: 0.896
- Procfile
- Contains the type of app.
- Requirements
- Libraries needed to run the app.
- Templates
- Files required for rendering purpose
- Static
- CSS styles
- App
- Main file which will run our Web App.
A thorough report on what we did can be found in FinalReport.md or FinalReport.pdf file.
Testing data for fraud transaction can be found in the "fraud_values.csv" file.
Testing data for a Valid transaction can be found in the "valid_values.csv" file.
The notebook used to train the model for this web app can be found
team members are: Albin Joy Thanjum Ken Liya Philipose