metadata
library_name: sklearn
license: mit
tags:
- tabular-classification
- sklearn
- wellness-tourism
datasets:
- jskswamy/wellness-tourism-data
metrics:
- accuracy
- f1
- precision
- recall
- roc_auc
model-index:
- name: GradientBoosting
results:
- task:
type: tabular-classification
name: Binary Classification
dataset:
name: Wellness Tourism Dataset
type: jskswamy/wellness-tourism-data
metrics:
- name: Accuracy
type: accuracy
value: 0.9346
- name: F1 Score
type: f1
value: 0.8163
- name: Precision
type: precision
value: 0.8911
- name: Recall
type: recall
value: 0.7531
- name: ROC AUC
type: roc_auc
value: 0.967
Wellness Tourism Package Prediction Model
This model predicts whether a customer will purchase the Wellness Tourism Package offered by "Visit with Us" travel company.
Model Description
- Model Type: GradientBoosting
- Task: Binary Classification
- Framework: scikit-learn
Intended Use
This model is designed to help travel companies identify potential customers for wellness tourism packages based on customer demographics and travel history.
Training Data
The model was trained on the Wellness Tourism Dataset containing customer information including:
- Demographics (Age, Gender, Marital Status)
- Professional details (Occupation, Designation, Monthly Income)
- Travel history (Number of Trips, Passport status)
- Pitch information (Duration, Property Star preference, Satisfaction Score)
Evaluation Results
| Metric | Value |
|---|---|
| Accuracy | 0.9346 |
| F1 Score | 0.8163 |
| Precision | 0.8911 |
| Recall | 0.7531 |
| ROC AUC | 0.9670 |
Usage
import joblib
from huggingface_hub import hf_hub_download
# Download model
model_path = hf_hub_download(
repo_id="jskswamy/wellness-tourism-model",
filename="wellness_tourism_model.joblib"
)
# Load and use
model = joblib.load(model_path)
predictions = model.predict(your_data)
Limitations
- Model performance may vary on data significantly different from the training distribution
- Predictions should be used as one factor among many in business decisions