Task 3: Linear Regression - Housing Price Prediction

Objective

Build and evaluate a Linear Regression model to predict housing prices based on various independent features. This task demonstrates preprocessing, feature engineering, model training, evaluation, and result interpretation.

Dataset

• Name: Housing.csv
• Source: Kaggle Dataset
• Target Variable: price

ools & Libraries Used

• Python
• Pandas
• NumPy
• Matplotlib
• scikit-learn

Workflow

1. Data Loading: Imported the dataset using Pandas.
2. Exploratory Analysis: Checked data types, missing values, and basic statistics.
3. Preprocessing:
   • One-hot encoded categorical variables using get_dummies().
   • Split data into independent variables (X) and target variable (y).
4. Train-Test Split: Used train_test_split to divide the data into 80% training and 20% testing sets.
5. Model Building: Trained a Linear Regression model using LinearRegression() from scikit-learn.
6. Evaluation:
   • MAE (Mean Absolute Error)
   • MSE (Mean Squared Error)
   • R² Score
7. Visualization:
   • Scatter plot of Actual vs Predicted values
8. Interpretation: Analyzed the coefficients of the trained model to understand feature impact.

Results

The model successfully predicted housing prices with a decent R² score and low error metrics. The output included coefficient values for each feature, indicating their influence on price prediction.

Files

• task3_linear_regression.ipynb – Jupyter Notebook with full code and explanations
• Housing.csv – Dataset used
• README.md – Project documentation

Completed on

August 7, 2025

Acknowledgments

This task was completed as part of my AI/ML internship to practice real-world applications of regression techniques.