Our project is a forecasting study created with the dataset used in the data science competition at Kaggle.
This study was prepared as a training project within the scope of Miuul Data Analyst Bootcamp. https://miuul.com/
Team Members 👩💻👨💻
Educators 👨🔬
- The objective of the project is to develop a house price prediction model that can provide accurate estimates for customers.
- The target audience includes potential home buyers and sellers.
- Gather and explore the data
- Assess the quality, completeness, and reliability of the data
- Identify any data issues, missing values, or outliers that need to be addressed
- Handling missing values, outliers, and inconsistencies.
- Perform feature engineering.
- Split the data into training and test sets and perform feature selection.
- Linear regression, random forests, XGBoost and LGBM Boosting
- Hyperparameter Tunning
- Evaluate the models using MSE, RMSE, MAE, MAPE and R-squared
- Learning Curve
- Interpret and analyse the model's results and assess its reliability and robustness.
- Integrate the house price prediction model into a production environment or a user-friendly application.
- Develop documentation and provide guidelines for the model's usage and maintenance.
More than 20 variables were used in the modeling phase of the project. After all, this is an educational project, we made prediction with only 8 variables to avoid a laborious process by including all variables on the Streamlit screen.