A Supervised Classification Algorithm used to observe discrete set of classes.
It uses the concept of probability and is a predictive analysis algorithm mostly binary classification.
The cost function used is usually Sigmoid function.
This is the general expression of sigmoid function. It limits or normalizes the values from 0 to 1. This can be much better understood from the below graph.
The most updated and hot real life scenario can be whether a person is likely infected by COVID or not. We can have two possible outcomes to this scenario - yes they are infected, or no they are not infected. An example of binary classification. Now there are two sorts of variables Independent and dependent variables.
- Independent Variables : Viral load, symptoms, and antibodies as in this case of COVID
- Dependent Variable : The Outcome (binary true or false) of the respective case.
In the real world, you can see logistic regression applied across multiple areas and fields.
- In health care, logistic regression can be used to predict if a tumor is likely to be benign or malignant.
- In the financial industry, logistic regression can be used to predict if a transaction is fraudulent or not.
- In marketing, logistic regression can be used to predict if a targeted audience will respond or not.