Skip to main content

​
Flask Application

The Fraud Detection ML System is built using Flask, a lightweight Python web framework. The API provides endpoints for training machine learning models and making predictions on fraud detection datasets.

​
Base URL

http://127.0.0.1:5001
The default port is 5001, but can be configured using the PORT environment variable.

​
Available Endpoints

The API exposes the following endpoints:

GET /

Access the web interface for fraud prediction

POST /train

Train a new fraud detection model using data from a specified folder

POST /predict

Make predictions on new data using the trained model

GET /dashboard

Access the Flask monitoring dashboard for performance metrics

​
Authentication

Currently, the API does not require authentication. All endpoints are publicly accessible.
In a production environment, you should implement proper authentication and authorization mechanisms to secure these endpoints.

​
CORS Configuration

Cross-Origin Resource Sharing (CORS) is enabled for all endpoints using flask-cors. All origins are currently allowed via: 
from flask_cors import CORS, cross_origin

CORS(app)
Each endpoint is also decorated with @cross_origin() to handle preflight requests.

​
Monitoring Dashboard

The application includes Flask Monitoring Dashboard for tracking API performance and usage: 
import flask_monitoringdashboard as dashboard
dashboard.bind(app)

​
Error Handling

All endpoints implement comprehensive error handling for:
  • ValueError - Invalid input values
  • KeyError - Missing required parameters
  • Exception - General exceptions
Error responses are returned as plain text with descriptive messages.

Build docs developers (and LLMs) love

Get started for freeTalk to us