Logistic RegressionwithMathematicalExamplesonit.pdf

This document i about the Logistic Regression. it includes the needs for Logistic Regression , Logistic Function, Sigmoid Function, Virtual Representions, Advantages, and disadvantages, Applications Of Logistic Regression, mathemtical examples for better understanding .

1. LOGISTIC
REGRESSION
(BINARY
CLASSIFICATIO )

2. NEED OF LOGISTIC
REGRESSION
•In linear regression, dependent variable is continuous.
•If we add an outlier in our dataset, the best fit line in linear
regression shiftsto fit that point.

3. •The predictive values may be outof range (may exceed 1 or go
below 0).

4. LOGISTIC REGRESSION
•SupervisedMachine Learning technique.
•Used for solving the binary classification problems.
•Predicts the output of a categoricaldependent variable.
•Outcome must be
categorical or discrete
value. It can be either
Yesor No.

5. LOGISTIC FUNCTION
•Also called SigmoidFunction.
•Maps any real value into another value within a
range of 0 and 1.
•It forms a curve like the ‘S’ shape. This S-shaped
curve is called the Sigmoid or Logistic function.
•Use the concept of
threshold value,
defines the probability
of either 0or 1.
(Default threshold value

6. •Equationof sigmoid function is:
where,
y= dependent variable
e= Euler’s constant (value: 2.178)
x= independent variable

7. DERIVATION OF
SIGMOID FUNCTION
•Equationof best-fit line in linear regression is:
•Take ‘odds’ of P:

8. •Take the ‘log of odds’:
•Multiply by exponenton both sides:

11. EXAMPLE
•Predict whether or not
the patient has diabetes
on the base of blood
glucose level.

13. APPLICABLE IN WHICH
FIELDS:
•Spam or not spam emails.
•Fraud detection.
•Disease diagnosis.

14. DRAWBACKS
•Logistic regression failsto predict a continuousoutcome.
•Notworks well for cases where the dataset is not linearly
separable.
•May not be accurate when the dataset is too small.

15. THANK
YOU!