Yacht Data Insights & Prediction 🚢📊

📌 Project Overview

This project aims to analyze and predict trends in yacht sales, weather conditions, and routes to optimize maintenance schedules and sales strategies. By leveraging data analysis and machine learning techniques, it provides actionable insights to help yacht companies plan more effectively and reduce waste in maintenance operations.

🛠 Tools & Technologies

• Python 🐍
• Pandas, NumPy, Scikit-learn 📊
• Matplotlib, Seaborn 📈
• XGBoost, Random Forest, Linear Regression 🧠
• Jupyter Notebook 💻

🌱 Eco-friendly Impact

This project helps companies reduce maintenance waste and improve their planning processes, leading to more sustainable business practices within the yacht industry.

🚀 Outcome

The goal is to develop a predictive model that supports:

• Scheduled maintenance by predicting potential issues based on historical data.
• Sales strategies by forecasting trends in yacht prices, demand, and seasonality.

---

📂 Project Structure

yacht-data-insights/ ├── 📂 ..bfg-report/2025-03-15 # Report folder with results and models ├── 📂 data/ # Raw datasets (sales, weather, routes) │ ├── 📂 raw/ # Folder containing dataset files │ └── 📜 data_description.md # Description of datasets ├── 📂 notebooks/ # Jupyter Notebooks folder for a modular and reproducible workflow │ ├── 📜 01_project_introduction.ipynb # Project overview, goals, datasets, and research questions │ ├── 📜 02_data_preprocessing.ipynb # Data loading, cleaning, encoding, splitting, and scaling │ ├── 📜 03_feature_engineering_and_exploration.ipynb # Feature creation and exploratory data analysis (EDA) │ └── 📜 04_modeling.ipynb # Regression/classification modeling and evaluation ├── 📜 .gitattributes # Git attributes file ├── 📜 .gitignore # Git ignore file ├── 📜 LICENSE # License file ├── 📜 README.md # Project documentation (this file)

Key sections:

• ..bfg-report/2025-03-15/: This folder contains your results, models, and other related reports.
• data/: Holds your datasets, with a subfolder for raw data and a description file.
• notebooks/: Contains Jupyter Notebooks for a modular and reproducible workflow:
  • 01_project_introduction.ipynb: Project overview, goals, datasets, and research questions.
  • 02_data_preprocessing.ipynb: Data loading, cleaning, encoding, splitting, and scaling.
  • 03_feature_engineering_and_exploration.ipynb: Feature creation and exploratory data analysis (EDA).
  • 04_modeling.ipynb: Regression/classification modeling and evaluation.
• .gitattributes & .gitignore: Configuration files for Git management.
• LICENSE & README.md: Project's licensing and docume

### 📈 **Data**
This project uses multiple datasets related to yacht sales, weather conditions, and routes. The datasets are cleaned, preprocessed, and analyzed to derive useful insights and predictions.

### 🧠 **Machine Learning Models**
- **Regression Models**: Linear Regression, Random Forest, and Support Vector Regression (SVR) for predicting yacht prices or sales trends.
- **Classification Models**: Logistic Regression, Random Forest, and SVM (optional) for categorizing yachts based on demand.
- **Optimization**: Hyperparameter tuning with GridSearchCV, and feature selection using SHAP values for interpretability.

### 📊 **Visualizations**
Key visualizations are generated to help stakeholders:
- Identify trends like price vs. size, seasonal demand, and route popularity.
- Visualize model predictions for better decision-making in sales and maintenance planning.

---

### 📬 **Contact**
📧 **Email**: [michelad.monteverde@gmail.com]  
📌 **GitHub**: [Michela999](https://github.com/Michela999)

---

### 📢 **Contributing**
This project is open to contributions. Feel free to create issues or submit pull requests for improvements or suggestions!

---

**Note**: This project is under development, and additional features and models may be added in the future.