Multiple Linear Regression

One input feature → One output

In Multiple Linear Regression:

Multiple input features → One output

Real-Life Example

Suppose we want to predict house price using:

• House area

• Number of bedrooms

• Age of house

Here:

• Multiple input variables affect the output

• A single feature is not enough for accurate prediction

Example Dataset

Where:

• Area

• Bedrooms

• Age

are input features and:

Price

is the target variable.

Why Multiple Linear Regression is Needed

Real-world problems usually depend on multiple factors.

For example:

• Salary depends on experience, education, and skills

• House price depends on location, area, and amenities

• Sales depend on marketing, price, and season

Using multiple features helps improve prediction accuracy.

Multiple Linear Regression Equation

y = b0 + b1x1 + b2x2 + b3x3 + ...

Where:

• y → Predicted output

• b0 → Intercept

• b1, b2, b3 → Coefficients

• x1, x2, x3 → Input features

Suppose:

Price = 10 + 0.05(Area) + 5(Bedrooms) - 2(Age)

This means:

• Larger area increases price

• More bedrooms increase price

• Older houses reduce price

Mathematical Example

Suppose we have:

Assume the model learned:

Price = 5 + 0.04(Area) + 3(Bedrooms)

Prediction Example

Predict house price for:

Area = 1400
Bedrooms = 3

Substitute values:

Price = 5 + 0.04(1400) + 3(3)

Calculate:

0.04 * 1400 = 56
3 * 3 = 9

Final prediction:

Price = 5 + 56 + 9

Price = 70

Practical Example Using Python

Step 1: Import Libraries

import pandas as pd
from sklearn.linear_model import LinearRegression

Step 2: Create Dataset

data = {
    "Area": [1000, 1200, 1500, 1800],
    "Bedrooms": [2, 3, 3, 4],
    "Age": [5, 4, 3, 2],
    "Price": [50, 60, 75, 90]
}

df = pd.DataFrame(data)

print(df)

Step 3: Define Features and Target

X = df[["Area", "Bedrooms", "Age"]]

y = df["Price"]

Step 4: Train Model

model = LinearRegression()

model.fit(X, y)

Step 5: Predict New Value

prediction = model.predict([[1400, 3, 3]])

print(prediction)

Expected Output

[70.]

Understanding Model Coefficients

print(model.coef_)

This gives:

• Effect of each feature on prediction

Intercept

print(model.intercept_)

This gives:

b0 value

Feature Importance

In Multiple Linear Regression:

• Each feature contributes differently

• Larger coefficient means stronger impact

Example:

This means:

• Bedrooms strongly increase price

• Age decreases price

Advantages

• Uses multiple features

• Better prediction accuracy

• Models real-world problems effectively

• Easy to interpret

Limitations

• Sensitive to outliers

• Multicollinearity may occur

• Assumes linear relationship

Real-World Applications

Important Points

1. Multiple Linear Regression uses multiple input features.

2. It predicts continuous numerical values.

3. Each feature has its own coefficient.

4. The regression equation contains multiple variables.

5. It is an extension of Simple Linear Regression.

Summary

Multiple Linear Regression is a supervised learning algorithm used to predict continuous numerical values using multiple input features. It helps model real-world problems more accurately by considering the combined effect of several variables on the target output.

Keywords

Multiple Linear Regression, Multiple Regression, Multiple Linear Regression in Machine Learning, Regression with Multiple Variables, Supervised Learning Regression, Multiple Feature Prediction, Regression Coefficients, Linear Regression using Python, Regression Model, Predictive Modeling, House Price Prediction, Multivariable Regression, Regression Analysis, Scikit Learn Linear Regression, Machine Learning Regression