A Streamlit-powered Machine Learning App for Ames Housing Price Prediction
Lydia Doe has inherited four houses located in Ames, Iowa.
She has little knowledge of the local housing market, and inaccurate pricing could lead to significant financial loss.
- Identify which house attributes (features) are most strongly correlated with the sale price.
- Build a predictive system where users can input house attributes and obtain an estimated sale price.
- Data analysis must clearly highlight relationships between attributes and sale price.
- The predictive model should achieve R² ≥ 0.75 on both train and test sets.
- Deliver an interactive Streamlit dashboard where users can explore insights and make predictions.
- Lydia will be able to maximize the sales price for her inherited properties.
- In the future, she can make data-driven decisions when buying or selling properties in the Ames market.