House-Price-Prediction---Regression-Model

🏠 House Price Prediction – Regression Model

This project is part of my internship at Codveda Technologies, where I built a Linear Regression model using Python and Scikit-learn to predict housing prices based on real estate features.

---

📁 Dataset

The dataset used is the Boston Housing Dataset, which includes information about housing in Boston suburbs. It consists of 13 numerical features and a target variable MEDV (Median house value in $1000s).

Features include:

• CRIM: Crime rate by town
• RM: Average number of rooms per dwelling
• AGE: Proportion of owner-occupied units built before 1940
• LSTAT: % lower status of the population
• … and more

---

🧠 Objective

• Perform data loading and preprocessing
• Build and train a Linear Regression model
• Evaluate model performance
• Visualize predicted vs. actual values

---

🛠️ Tools Used

• Python
• Pandas
• Matplotlib
• Seaborn
• Scikit-learn
• Jupyter Notebook

---

📊 Evaluation Metrics

• Mean Squared Error (MSE): 21.89
• R-squared (R²): 0.6688

The model explains approximately 66.88% of the variance in housing prices based on the selected features.

---

📈 Visualizations

• Actual vs. Predicted Prices (Scatter Plot)
• Histogram of feature distributions
• Heatmap of feature correlations

These visualizations help understand the relationship between input features and the target variable.

---

🏁 Status

✅ Completed
📁 Notebook: regression_house_prices.ipynb
🧠 Task Level: Intermediate – Codveda Internship Task 2

---

📢 Internship Credit

This project was completed as part of my Data Science Internship at Codveda Technologies.
Follow my journey with:

---

🔗 Connect with Me

📧 Email: radheverma146@gmail.com
🔗 GitHub: https://github.com/Radhe127
🔗 LinkedIn: https://linkedin.com/in/radheverma

This site is open source. Improve this page.