This project explores the factors influencing house prices in King County, USA, and develops a predictive model using linear regression. It aims to identify key property characteristics that affect pricing and provide actionable insights for buyers, sellers, and real estate professionals. Using publicly available housing data from Kaggle, this analysis focuses on variables such as total living area (sqft_living), house grade, bathrooms, view, and waterfront access. A combination of exploratory data analysis, correlation studies, and regression modeling is employed to understand and predict home values.
- Exploratory Data Analysis (EDA) to visualize trends and distributions
- Correlation analysis to identify strong predictors
- Simple and multiple linear regression modeling
- Model evaluation using R², RMSE, and MAE
- Insights into the effect of premium features like waterfront and view
This project applies multiple linear regression to predict house prices in King County, USA, and analyzes the extent to which this model can be reliably used for housing price estimation. The study highlights key predictors such as living area, grade, bathrooms, waterfront, and view, while evaluating model performance with metrics like R², RMSE, and MAE.
- sqft_living, house grade, and bathrooms are strong predictors of house price.
- Premium features such as waterfront and scenic views significantly increase home value.
- Multiple linear regression models can reasonably predict house prices, providing a practical tool for valuation.
This project builds upon my earlier work in data analysis with Python. You can view my previous related project here.