v1.0/README.md

metadata

license: mit
tags:
  - driver-behavior
  - obd-data
  - xgboost
  - rlhf
  - reinforcement-learning

Driver Behavior Classification Model (RLHF v1.0)

This model classifies driver behavior based on OBD (On-Board Diagnostics) sensor data using XGBoost.

Model Information

• Model Type: xgboost_classifier
• Version: 1.0
• Created: 2025-10-01T06:16:26.712373
• Framework: xgboost
• Task: driver_behavior_classification

Performance Metrics

• accuracy: 0.9216
• cv_mean: 0.5193
• cv_std: 0.1122
• cv_scores: [0.35789473684210527, 0.5578947368421052, 0.5, 0.4787234042553192, 0.7021276595744681]

Training Data

• Datasets Used: 2
• Total Samples: 472
• Training Date: 2025-10-01T06:16:26.711090

Labels

The model predicts one of the following driver behavior categories:

• aggressive
• normal
• conservative

Usage

import joblib
import pandas as pd

# Load the model
model = joblib.load('xgb_drivestyle_ul.pkl')
label_encoder = joblib.load('label_encoder_ul.pkl')
scaler = joblib.load('scaler_ul.pkl')

# Prepare your OBD data
# (Ensure features match the training data format)

# Make predictions
predictions = model.predict(scaled_data)
behavior_labels = label_encoder.inverse_transform(predictions)

Files

• xgb_drivestyle_ul.pkl: Main XGBoost model
• label_encoder_ul.pkl: Label encoder for behavior categories
• scaler_ul.pkl: Feature scaler
• metadata.json: Model metadata and performance metrics

RLHF Training

This model was trained using Reinforcement Learning from Human Feedback (RLHF) to improve performance based on human-labeled data and feedback.