In an exploration of Ames, Iowa's housing market, this project delved into a dataset with 79 variables to uncover the nuanced factors influencing home prices. Using heatmaps, key insights were revealed, highlighting the intricate relationship between property features and their market values.

The study then evaluated seven machine learning models to predict home prices accurately, with a focus on optimizing a Gradient Boosting model that achieved an R2 of 0.935. This approach not only demonstrated the project's analytical depth but also secured a top 65th percentile ranking in a competitive Kaggle challenge.

Machine Learning Model includes: