5 days left! Grow on your schedule with big savings on Coursera Plus. Save 40% for 3 months . Machine learning models power industries like data science, marketing, and finance. This guide covers how they're built, key algorithms, types of machine learning, model training parameters, and popular methods for classification and regression. Machine learning models are computer programs that recognize patterns in data and make predictions. Two types of machine learning models are classification (e.g., logistic regression, decision trees) and regression (e.g., linear regression, neural networks). Two types of machine learning models are classification (e.g., logistic regression, decision trees) and regression (e.g., linear regression, neural networks). Developers create machine learning models by using machine learning algorithms, which undergo a training process using either labeled, unlabeled, or mixed data. Developers create machine learning models by using machine learning algorithms, which undergo a training process using either labeled, unlabeled, or mixed data. You can use supervised, unsupervised, semi-supervised data, or reinforcement learning to train machine learning algorithms. You can use supervised, unsupervised, semi-supervised data, or reinforcement learning to train machine learning algorithms. Explore what machine learning models are, how to create them, and what types of popular algorithms act as their foundation. If you’re ready to expand your machine learning knowledge, enroll in the IBM Machine Learning Professional Certificate , where in as little as three months, you can learn about regression analysis, supervised learning, data science, deep learning, and more. What is a model in machine learning? Machine learning models are computer programs that are used to recognize patterns in data or make predictions. They are critical for everything from data science to marketing , finance, retail, and more. Today, the machine learning revolution has changed not only how businesses operate but entire industries as well. You create machine learning models by using machine learning algorithms , which undergo a training process using either labeled, unlabeled, or mixed data. Different machine learning algorithms suit different goals, such as classification or prediction modeling, so data scientists use different algorithms as the basis for different models. As you introduce data to a specific algorithm, it is modified to better manage a specific task and becomes a machine learning model. For example, a decision tree is a common algorithm used for both classification and prediction modeling. A data scientist looking to create a machine learning model that identifies different animal species might train a decision tree algorithm with various animal images. Over time, the algorithm would become modified by the data and increasingly better at classifying animal images. In turn, this would eventually become a machine learning model. Machine learning types: Models vs. algorithms Despite their differences, many people use these two terms interchangeably. Machine learning algorithms are programming procedures. They are methods created to solve a problem or complete a task. Machine learning models are the output of these procedures, containing the data and the procedural guidelines for using that data to predict new data. How to build a machine learning model You can create machine learning models by training algorithms with either labeled data, unlabeled data, or a mix of both. Four primary machine learning algorithms exist: 1. Supervised learning Training: Uses labeled data which is data tagged with a label so an algorithm can successfully learn from it. Training: Uses labeled data which is data tagged with a label so an algorithm can successfully learn from it. Purpose: Helps the algorithm classify data as desired. Purpose: Helps the algorithm classify data as desired. 2. Unsupervised learning Training: Uses unlabeled data. Training: Uses unlabeled data. Purpose: Algorithm finds patterns and creates data clusters. Purpose: Algorithm finds patterns and creates data clusters. 3. Semi-supervised learning Training: Combines labeled and unlabeled data. Training: Combines labeled and unlabeled data. Purpose: Algorithms are trained first with a small amount of labeled data, then with more unlabeled data. Purpose: Algorithms are trained first with a small amount of labeled data, then with more unlabeled data. 4. Reinforcement learning Training: Assigns positive and negative values to desired and undesired actions. Training: Assigns positive and negative values to desired and undesired actions. Purpose: Encourages programs to maximize rewards through trial and error and avoid the negative training examples. Purpose: Encourages programs to maximize rewards through trial and error and avoid the negative training examples.

What are parameters in machine learning models? Before machine learning engineers train a machine learning algorithm, they must first set the hyperparameters for the algorithm, which act as external guides that inform the decision process and direct how the algorithm will learn. For instance, the number of branches on a regression tree, the learning rate, and the number of clusters in a clustering algorithm are all examples of hyperparameters. Read more: What Are Hyperparameters? As the algorithm is trained and directed by the hyperparameters, parameters form in response to the training data. These parameters include the weights and biases formed by the algorithm during training. The final parameters for a machine learning model are the model parameters, which ideally fit a data set without going over or under. While you can identify a machine learning model’s parameters, you can’t identify the hyperparameters used to create it. Types of machine learning models Two types of problems dominate machine learning: classification and prediction. You can approach these problems using models derived from algorithms designed for either classification or regression (a method used for predictive modeling). The same algorithm can occasionally be useful for classification or regression models, depending on its training. Explore the following list of popular algorithms for classification and regression models. Machine learning classification models Logistic regression Logistic regression K-nearest neighbor (KNN) K-nearest neighbor (KNN) Support vector machine Support vector machine Machine learning regression models Linear regression Linear regression Ridge regression Ridge regression K-nearest neighbor (KNN) K-nearest neighbor (KNN) Neural network regression Neural network regression Keep up with trends and tips in machine learning Subscribe to our weekly LinkedIn newsletter, Career Chat , for industry updates, tips, and trends. Then, explore free, machine learning and AI resources to optimize your professional growth: Watch on YouTube: Career Spotlight: Machine Learning Engineer Watch on YouTube: Career Spotlight: Machine Learning Engineer Explore career paths: Machine Learning Career Paths: Explore Roles & Specializations Explore career paths: Machine Learning Career Paths: Explore Roles & Specializations Learn related terminology: Artificial Intelligence Glossary: Learn AI Vocabulary Learn related terminology: Artificial Intelligence Glossary: Learn AI Vocabulary With Coursera Plus , you can learn and earn credentials at your own pace from over 350 leading companies and universities. With a monthly or annual subscription, you’ll gain access to over 10,000 programs—just check the course page to confirm your selection is included. Break down barriers to learning with big savings Get Coursera Plus Break down barriers to learning with big savings Coursera’s editorial team is comprised of highly experienced professional editors, writers, and fact... This content has been made available for informational purposes only. Learners are advised to conduct additional research to ensure that courses and other credentials pursued meet their personal, professional, and financial goals.