Real estate is a dynamic market with fluctuating prices influenced by various factors. The goal of this project is to build a predictive model that can help Wazobia Real Estate Limited in Nigeria determine the optimal pricing for properties based on specific features like location, title, number of bedrooms, bathrooms, and parking space.

The cross-validated Catboost regressor model with an RMSE of 543,725 was chosen as the model of choice for the prediction because it had the lowest RMSE score and showed a strong generalization ability as it performed well on multiple folds of data and hence can adapt better to unseen data.

Feature importance analysis was conducted on the cross-validated Catboost regressor model to identify which features have the most significant impact on house prices. This analysis provides valuable insights into the factors that drive property prices in Nigeria. The top three features that significantly impact house prices are The Title, Location, and number of bedrooms. Other contributing features inclde: Population density level, total number of rooms (bedroom, bathroom, parking space), and ratio of the bedroom to the bathroom.

This data science project successfully predicts house prices for the real estate company based on essential features like location, title, and amenities. The top-performing model is the Cross-validated Catboost regressor.