buymydreamhome.com is our client. They sell properties along all US. BMDH has several hundreds thousands of properties listed in his databases. For the future they want to create a tool that helps agents and clients to set a price. The idea is that a tool suggest a price for the future possible property. In one hand clients would have an orientation about the value of their real state. In the other hand agents can check and give advice to customers to put a reasonable price to the properties listed.
Goal - With the data provided create a model that predict the price of the property with the relevant features.
Workflow - https://trello.com/b/WdTgmLi1/housing-price-prediction
Presentation - https://docs.google.com/presentation/d/1967QeKdE37LV35zL8OrKrGHKhAwBgxg_gqPtTUcOMRw/edit
Jupyter Notebook - https://github.com/lj90pot/Mid_project_chilli_flakes/tree/main/Python_Notebook
ARTICLES
- https://scikit-learn.org/stable/auto_examples/ensemble/plot_gradient_boosting_regression.html
- https://machinelearningmastery.com/xgboost-for-regression/
- https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html
- https://towardsdatascience.com/random-forest-regression-5f605132d19d
- https://www.nvidia.com/en-us/glossary/data-science/xgboost/
- https://towardsdatascience.com/https-medium-com-vishalmorde-xgboost-algorithm-long-she-may-rein-edd9f99be63d
Gradient Boosting regression https://scikit-learn.org
Tech stack!
- Python
- Pandas
- Numpy
- Matplotlib
- Seaborn
- Sklearn
- XGBoost
- MYSQL
- Tableau Public