metadata

tags:
  - fraud-detection
  - random-forest
  - sklearn
library_name: sklearn
pipeline_tag: tabular-classification

Random Forest Fraud Detection Model

This model uses Random Forest classification to detect potential fraud based on various account and transaction features.

Model Description

Input Features:
- Account Age (months)
- Frequency of credential changes (per year)
- Return to Order ratio
- VPN/Temp Mail usage (binary)
- Credit Score
Output: Binary classification (Fraud/Not Fraud)
Type: Random Forest Classifier

Usage

import joblib
import numpy as np

# Load model and scaler
model = joblib.load('random_forest_model.joblib')
scaler = joblib.load('rf_scaler.joblib')

# Prepare input (example)
input_data = np.array([[25, 0.5, 0.4, 0, 800]])

# Scale input
scaled_input = scaler.transform(input_data)

# Get prediction
prediction = model.predict(scaled_input)
probability = model.predict_proba(scaled_input)

Limitations and Bias

This model should be used as part of a larger fraud detection system and not in isolation.