P-Mishra/tourism_package_prediction

Tourism Package Prediction Model

Model Overview

This repository contains the best performing machine learning model for predicting customer purchases of the Wellness Tourism Package.

Best Model Details

• Model Type: XGBoost
• Best Hyperparameters:

{
    "xgboost__colsample_bytree": 0.8,
    "xgboost__learning_rate": 0.2,
    "xgboost__max_depth": 7,
    "xgboost__n_estimators": 100
}

Performance Metrics (Test Set)

• Accuracy: 0.9443
• Precision: 0.8742
• Recall: 0.8424
• F1-Score: 0.8580

Features Used

The model was trained on preprocessed customer and interaction data, including (but not limited to) features such as Age, TypeofContact, CityTier, Occupation, Gender, NumberOfPersonVisiting, PreferredPropertyStar, MaritalStatus, NumberOfTrips, Passport, OwnCar, NumberOfChildrenVisiting, Designation, MonthlyIncome, PitchSatisfactionScore, ProductPitched, NumberOfFollowups, and DurationOfPitch.

Usage

To use this model for inference:

import joblib
import pandas as pd

# Load the model
model = joblib.load('best_tourism_package_model.joblib')

# Prepare your input data (ensure it matches the training data format)
# Example (replace with actual data structure after preprocessing):
# new_data = pd.DataFrame(...)

# Make a prediction
# prediction = model.predict(new_data)
# print(prediction)