https://github.com/justfifi17/nyc-real-estate-sales-prediction

Analyzes real estate sales data in NYC by performing exploratory data analysis and building models to predict sale prices based on various features.
https://github.com/justfifi17/nyc-real-estate-sales-prediction

data-visualization exploratory-data-analysis gradient-boosting linear-regression random-forest xgboost-regression

Last synced: about 6 hours ago
JSON representation

Analyzes real estate sales data in NYC by performing exploratory data analysis and building models to predict sale prices based on various features.

• Host: GitHub
• URL: https://github.com/justfifi17/nyc-real-estate-sales-prediction
• Owner: justfifi17
• Created: 2024-10-16T04:50:49.000Z (23 days ago)
• Default Branch: main
• Last Pushed: 2024-10-16T05:30:05.000Z (23 days ago)
• Last Synced: 2024-10-17T19:38:44.834Z (21 days ago)
• Topics: data-visualization, exploratory-data-analysis, gradient-boosting, linear-regression, random-forest, xgboost-regression
• Language: Jupyter Notebook
• Homepage:
• Size: 1.17 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# 🏙 NYC Real Estate Sales Prediction

This project uses **machine learning models** to predict real estate sales prices in New York City from 2016-2017. The dataset includes property details like borough, neighborhood, building class, and sales prices.

## Models used 

- Linear Regression

- Random Forest Regressor

- Gradient Boosting Regressor

- XGBoost Regressor

 

## 📊 Features

- **Data Preprocessing**: Handled missing values, removed unnecessary columns, and transformed skewed data using log transformation.

- **Modeling**: Developed models using **Linear Regression**, **Random Forest**, **Gradient Boosting**, **XGBoost**, and others.

- **Best Model**: Random Forest with **RMSE** of 0.45 and **R²** of 0.76 was chosen for its strong performance and feature importance insights.

## 🛠️ Technologies Used

- **Python**: Core language.

- **Pandas, NumPy**: Data manipulation.

- **Seaborn, Matplotlib**: Visualization.

- **Scikit-learn, XGBoost**: Machine learning algorithms.

## 🚀 How to Run

1. Clone this repository:

   ```bash

   git clone 

2. Install dependencies:

   ```bash

   pip install -r requirements.txt

3. Run the model:

   ```bash

   python real_estate_sales_prediction.py

## 📈 Results

- Random Forest achieved the best results with an R² of 0.76.

- Featured models were evaluated based on RMSE and R².

## 🧪 Tests

- Train-Test Split: Split data into training (80%) and testing (20%) sets.

- Cross-validation: Performed 5-fold cross-validation to evaluate model performance.

- Hyperparameter Tuning: Used GridSearchCV to tune the hyperparameters for Random Forest and XGBoost models.

- Model Evaluation: Assessed models based on RMSE, MAE, and R².