Logistic Regression. Detailed Overview for Fintech challenges
This article is about Logistic Regression, How does it work, the benefits and challenges of logistic regression, Solving Fintech challenges with Machine Learning
--
This article is part of a series where we walk step by step through solving fintech problems with different Machine Learning techniques using the “All lending club loan” dataset. Here you can find the complete end-to-end data science project for beginners to learn data science.
📌 Introduction
Suppose we are trying to solve a problem where we want to predict, based on input data, the likelihood that a person will pay a loan back or charge off. This type of problem is called a classification problem, where we need to find the probability that an event will occur or not, or whether it will be true/false. To solve this problem, we often use the most popular supervised ML algorithm Logistic Regression Model.
📌 What is Logistic Regression, and how does it work?
Logistic regression predicts a probability of a categorical dependent variable. It is a statistical method to analyze data with one or more independent variables determining the outcome. The outcome is typically two possible options we target to predict as a binary value: 1 or 0, yes or no, true or false, given a set of independent variables.
You can consider Logistic Regression as some case of Linear Regression when the actual variable is categorical and where we use the log probabilities as the dependent variable. Say it simply, it predicts the probability of an event by fitting data to the logit function.
Be aware that in some cases, the dependent variables may have more than two outcomes, e.g. married, single or divorced. Such scenarios are classified as polynomial logistic regression. Note that they work the same way to predict the outcome.
Logistic regression is a very efficient mechanism for computing probabilities. To understand more, let’s go through the mathematical foundations of logistic regression.
