Machine Learning Models: What They Are and How to Build Them

Written by Coursera Staff • Updated on

Machine learning models are the backbone of innovations from finance to retail. Read on to find out more.

[Featured Image]:  A woman with long dark hair and wearing a gray turtleneck sweater. She is sitting in front of two computer screens and is wearing white headphones.

Machine learning models are critical for everything from data science to marketing, finance, retail, and more. Today, only some industries are untouched by the machine learning revolution, which has changed how whole businesses operate and industries.

But what are machine learning models? And how are they built?

In this article, you will learn how machine learning models are created and find a list of popular algorithms that act as their foundation. You'll also find suggested courses and articles to guide you toward machine learning mastery. 

What is a machine learning model?

Machine learning models are computer programs that recognise data patterns or make predictions.

Machine learning models are created from machine learning algorithms, which are trained using labelled, unlabelled, or mixed data. Different machine learning algorithms are suited to other goals, such as classification or prediction modelling, so data scientists use different algorithms as the basis for other models. As data is introduced to a specific algorithm, it is modified to manage a particular task better and becomes a machine learning model.

For example, a decision tree is a common algorithm for both classification and prediction modelling. 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. 

How to build a machine learning model

Machine learning models are created by training machine learning algorithms with either labelled or unlabelled data or a mix of both. As a result, there are three primary ways to train and produce a machine-learning algorithm: 

  • Supervised learning: Supervised learning occurs when a machine learning algorithm is trained using "labelled data" or data tagged with a label to learn from it successfully. Training an algorithm with labelled data helps the eventual machine learning model classify data as the researcher desires.

  • Unsupervised learning: Unsupervised learning uses unlabelled data to train an algorithm. In this process, the algorithm finds data patterns and creates clusters. Unsupervised learning is helpful for researchers looking to find patterns in data that are currently unknown to them.

  • Semi-supervised learning: Semi-supervised learning uses labelled and unlabelled data to train an algorithm. In this process, the algorithm is first trained with a small amount of labelled data before being trained with a much more significant amount of unlabelled data. 

What are the parameters of machine learning?

Before a researcher trains a machine learning algorithm, they must first set the hyperparameters for the algorithm, which act as external guides that direct how the algorithm will learn. For instance, hyperparameters are examples of the number of branches on a decision tree, the learning rate, and the number of clusters in a clustering algorithm. 

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 the algorithm forms as it is being trained. The final parameters for a machine learning model are called the model parameters, which ideally fit a data set without going over or under. 

While a machine learning model's parameters can be identified, the hyperparameters used to create it cannot.

Types of machine learning models

Two types of problems that dominate machine learning: classification and prediction. 

These problems are approached using models derived from algorithms designed for either classification or regression (a method used for predictive modelling). Occasionally, the same algorithm can be used to create either classification or regression models, depending on how it is trained. 

Below is a list of common algorithms for classification and regression models. 

Classification models in machine learning 

  • Logistic regression 

  • Naive Bayes 

  • Decision trees 

  • Random forest 

  • K-nearest neighbour (KNN)

  • Support vector machine

Regression models in machine learning

  • Linear regression

  • Ridge regression 

  • Decision trees

  • Random forest 

  • K-nearest neighbour (KNN)

  • Neural network regression

Learn more about machine learning. 

Enrolling in an online course can help you advance your career, whether you want to become a data scientist or deepen your understanding of neural networks.

In Stanford and DeepLearning.AI's Machine Learning Specialisation, you'll master fundamental AI concepts and develop practical machine learning skills in a beginner-friendly, three-course programme by AI visionary Andrew Ng.

Meanwhile, DeepLearning.AI’s Deep Learning Specialisation teaches you how to build and train neural network architecture and contribute to developing cutting-edge AI technology.

Keep reading

Updated on
Written by:

Editorial Team

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.