Logistic Regression : classification algorithm
- 2. Introduction logistic Regression : what , when and how ? Advantages and Disadvantages Uses cases Demo
- 3. Introduction What is Regression? Regression is one of the most common models of machine learning , it is a way of predicting future happenings between a dependent (target) and one or more independent (predictor) variables . 3 Regression Linear regression Logistic regression Polynomial regression
- 4. logistic Regression : What ? Logistic regression is a classification algorithm used to assign observations to a discrete set of classes , In other words,the outcome or target variable is dichotomous in nature , which means it can only have one of two values (either 0 or 1, true or false, black or white, spam or not spam, and so on … )
- 6. logistic Regression : How ? Logistic Regression predicts the probability of occurrence of a binary event utilizing what we call logit function or Sigmoid function . The hypothesis of logistic regression : ted will become 0.
- 7. The hypothesis of logistic regression : 1. Linear Regression fonction : 1. Sigmoid Function: 1. Apply Sigmoid function on linear regression:
- 8. Example Does a patient have a lung cancer ?
- 9. New Data
- 11. Optimization The Cost function of Logistic regression Cost Function The cost function represents optimization objective i.e. we create a cost function and minimize it so that we can develop an accurate model with minimum error.
- 12. Gradient Descent Gradient descent is an optimization algorithm , The main goal of it is to minimize the cost value. Objective: To minimize the cost function we have to run the gradient descent function on each parameter . 12
- 13. Uses Cases Logistic Regression has a wide range of real-life applications : medical fields 13 Social sciences Marketing fields
- 14. Advantages ❖ Useful on problems where you need to give more rationale for a prediction ❖ Doesn't require high computation power ❖ Easy to implement and to interpret ❖ Used widely by data analyst and scientist ❖ Logistic regression provides a probability score for observations
- 15. Disadvantages ❖ Logistic regression is not able to handle a large number of categorical features. ❖ Logistic regression will not perform well with independent variables that are not correlated to the target variable and are very similar or correlated to each other.
- 16. “ ▸ Thank you ! 16