Context:
“Visit with us” aims to expand its customer base by introducing a new Wellness Tourism Package. Currently offering five types of packages, the company observed an 18% purchase rate last year. High marketing costs due to random customer contact prompted the need for a data-driven approach to target potential buyers effectively.

Objective:
Predict customer likelihood of purchasing the new Wellness Tourism Package.
Identify key factors influencing purchase decisions.
Provide targeted marketing strategy recommendations.
Techniques:

Data Visualization: Seaborn, Matplotlib
Machine Learning Models: Decision Tree, Random Forest, AdaBoost, Gradient Boosting, XGBoost
Model Tuning: GridSearchCV for hyperparameter optimization
Evaluation Metrics: Precision, Recall, Accuracy, Confusion Matrix

Data: Customer Details: Age, Gender, Occupation, Marital Status, Monthly Income, etc.
Interaction Data: Type of Contact, Number of Follow-ups, Sales Pitch Duration, etc.
Product Data: Preferred Property Rating, Number of Persons Visiting, etc.

Domain: Tourism and Hospitality