This project focuses on developing a regression model to predict house prices based on various features from the House Sales Dataset. The analysis and modeling are thoroughly documented in the data_analysis.ipynb notebook, while the user-friendly web application is built using the Streamlit framework, and available in app.py.
The project leverages key tools from the data science ecosystem, including:
- Scikit-learn for model building and evaluation
- Pandas and NumPy for data manipulation and analysis
- Plotly for interactive visualizations
- Statsmodels for statistical analysis
- TensorFlow and Keras for deep learning model experimentation
The main goal is to create an accurate regression model that predicts house prices based on features such as location, size, number of bedrooms, and other relevant variables. This project combines both traditional machine learning techniques and deep learning approaches, with a full exploratory data analysis (EDA), feature engineering, model training, and performance evaluation pipeline.