-
-
Analysis Dashboard
Inspiration
Understanding real estate prices is challenging due to numerous influencing factors. We aimed to create a data-driven tool that helps buyers, sellers, and investors make informed decisions by analyzing key features like location, crime rates, and amenities.
How We Built It
- Data Collection & Cleaning: Processed real estate listings, handled missing values, and extracted key features.
- Model Development: Tested multiple models (XGBoost, Random Forest, KNN, Linear Regression) and optimized performance using hyperparameter tuning.
- Evaluation & Insights: Compared models using MAE and R² Score, built visualizations to highlight property trends.
Challenges & Learnings
- Handling missing data and selecting relevant features.
- Balancing model accuracy and interpretability.
- Understanding how external factors impact real estate prices.
Future Improvements
- Real-time market updates for better predictions.
- User-friendly web app for property insights.
- More location-based features, like safety ratings and economic trends.
Conclusion
This project bridges data and real estate to make smarter decisions!
Built With
- knn
- numpy
- pandas
- python
- random-forest
- scikit-learn
- scipy
- streamlit
- xgboost
Log in or sign up for Devpost to join the conversation.