This project explores the use of advanced machine learning models to identify undervalued and overvalued properties in the burgeoning real estate market of Nashville. The goal is to assist a real estate company in making strategic investment decisions by leveraging predictive analytics.

1. Data Preprocessing:
   • Comprehensive data cleansing, feature engineering, and outlier treatment.
2. Predictive Modeling:
   • Logistic Regression, Decision Trees, Random Forests, and Gradient Boosting.
3. Model Evaluation:
   • Comparing models using metrics like accuracy, precision, recall, and AUC-ROC scores.
4. Business Recommendations:
   • Actionable insights based on model outputs for real estate investment strategies.

• Best Performing Model: The Gradient Boosting Model achieved the highest predictive accuracy, followed closely by Random Forests.
• Important Features:
  • Building Value, Land Value, and Time Since Sale were among the most influential factors.
• Business Impact:
  • Provided a reliable method to identify undervalued properties, maximizing investment returns.

For a detailed analysis, including methodology, visualizations, and insights, refer to the complete project report:
📄 Investing in Nashville Using Machine Learning

.
├── Data/
│   ├── Nashville_Housing_Data.csv
├── Scripts/
│   ├── investing_nashville.py
│   ├── eda_visualizations.py
├── Models/
│   ├── logistic_regression_model.pkl
│   ├── random_forest_model.pkl
│   ├── gradient_boosting_model.pkl
├── Reports/
│   ├── Investing_in_Nashville_Report.pdf
├── README.md

Feel free to reach out for feedback, questions, or collaboration opportunities:
LinkedIn: Dr. Syed Faizan

Author: Syed Faizan
Master’s Student in Data Analytics and Machine Learning