11/6/24, 20:19 What is machine learning?

| Microsoft Azure

Azure Explore Search 

Products
What is machine learning? 

Solutions The science of training machines to analyze and learn from data the way humans do.

Pricing

Partners

More

sub-navigation 

What is machine learning and how does it work?

Machine learning (ML) is the process of using mathematical models of data to help a computer learn without direct instruction. It’s considered a
subset of artificial intelligence (AI). Machine learning uses algorithms to identify patterns within data, and those patterns are then used to create a
data model that can make predictions. With increased data and experience, the results of machine learning are more accurate—much like how
humans improve with more practice.

The adaptability of machine learning makes it a great choice in scenarios where the data is always changing, the nature of the request or task are
always shifting, or coding a solution would be effectively impossible.

 Chat with sales

https://azure.microsoft.com/en-us/resources/cloud-computing-dictionary/what-is-machine-learning-platform/ 1/6
11/6/24, 20:19 What is machine learning? | Microsoft Azure

How machine learning relates to AI

Machine learning is considered a subset of AI. An “intelligent” computer thinks like a human and carries out tasks on its own. One way to train a
computer to mimic human reasoning is to use a neural network, which is a series of algorithms that are modeled after the human brain.

How machine learning relates to predictive analytics

Although machine learning is a type of predictive analytics, a notable nuance is that machine learning is significantly easier to implement with real-time
updating as it gains more data. Predictive analytics usually works with a static dataset and must be refreshed for updates.

How machine learning relates to deep learning

Deep learning is a specialized form of machine learning, using neural networks (NN) to deliver answers. Able to determine accuracy on its own, deep
learning classifies information like a human brain—and powers some of the most human-like AI.

The benefits of machine learning

Machine learning has many applications—and the possibilities are constantly expanding. Here are some of the top benefits that businesses have
achieved with their machine learning projects:

Uncover insight
Machine learning can help identify a pattern or structure within both structured and unstructured data, helping to identify the story the data is telling.

Improve data integrity

Machine learning is excellent at data mining and can take it a step further, improving its abilities over time.

Enhance user experience

Adaptive interfaces, targeted content, chatbots, and voice-enabled virtual assistants are all examples of how machine learning can help optimize the
customer experience.

Reduce risk
As fraud tactics constantly change, machine learning keeps pace—monitoring and identifying new patterns to catch attempts before they’re successful.


https://azure.microsoft.com/en-us/resources/cloud-computing-dictionary/what-is-machine-learning-platform/ 2/6
11/6/24, 20:19 What is machine learning? | Microsoft Azure

Anticipate customer behavior

Machine learning can mine customer-related data to help identify patterns and behaviors, letting you optimize product recommendations and provide
the best customer experience possible.

Lower costs
One machine learning application is process automation, which can free up time and resources, allowing your team to focus on what matters most.

Machine learning techniques

Supervised learning
Addressing datasets with labels or structure, data acts as a teacher and “trains” the machine, increasing in its ability to make a prediction or decision.

Unsupervised learning
Addressing datasets without any labels or structure, finding patterns and relationships by grouping data into clusters.

Reinforcement learning
Replacing the human operator, an agent—a computer program acting on behalf of someone or something—helps determine outcome based upon a
feedback loop.

How machine learning works to solve problems

Here is an overview of the machine learning process that is used to solve problems:

Step 1: Collect and prepare the data

Once data sources are identified, available data is compiled. The type of data that you have can help inform which machine learning algorithms you can
use. As you review your data, anomalies are identified, structure is developed, and data integrity issues are resolved.

Step 2: Train the model

The prepared data is split into two groups: the training set and the test set. The training set is a large portion of your data that’s used to tune your
machine learning models to the highest accuracy.


https://azure.microsoft.com/en-us/resources/cloud-computing-dictionary/what-is-machine-learning-platform/ 3/6
11/6/24, 20:19 What is machine learning? | Microsoft Azure

Step 3: Validate the model

When you’re ready to select your final data model, the test set is used to evaluate performance and accuracy.

Step 4: Interpret the results

Review the outcome to find insights, draw conclusions, and predict outcomes.

What can machine learning do?

Predict values Identify unusual occurrences

Helpful in identifying cause and effect between variables, regression Often used to spot potential risk, anomaly detection algorithms pinpoint
algorithms create a model from values, which are then used to make a data outside anticipated norm. Equipment malfunction, structural defect,
prediction. Regression studies help forecast the future, which can help text errors, and instances of fraud are examples of how machine learning
anticipate product demand, predict sales figures, or estimate campaign can be used to address concern.
results.

Find structure Predict categories

Clustering algorithms are often the first step in machine learning, Classification algorithms help determine the correct category for
revealing the underlying structure within the dataset. Categorizing information. Bearing similarity to clustering, classification is different in
common items, clustering is commonly used in market segmentation, that it is applied in supervised learning, where predefined labels are
offering insight that can help select price and anticipate customer assigned.
preferences.

What does a machine learning engineer do?

Machine learning engineers work translate the raw data gathered from various data pipelines into data science models that can be applied and scaled
as needed. A machine learning engineer connects that structured data to the models defined by the data scientists they work with. In addition, machine
learning engineers also develop algorithms and build programs that enable machines, computers, and robots to process incoming data and identify
patterns.

A brief primer on machine learning algorithms


https://azure.microsoft.com/en-us/resources/cloud-computing-dictionary/what-is-machine-learning-platform/ 4/6
11/6/24, 20:19 What is machine learning? | Microsoft Azure

Machine learning algorithms identify patterns within data, helping data scientists solve problems. Machine learning algorithms can predict values,
identify unusual occurrences, determine structure, and create categories. Depending upon the type of data you have and the outcome you’re looking
for, you’ll use different algorithms. Algorithms are typically grouped by technique (supervised learning, unsupervised learning, or reinforced) or by
family of algorithm (including classification, regression, and clustering). Learn more about machine learning algorithms.

How different industries use machine learning

Businesses across industries are using machine learning in a wide variety of ways. Here are some examples of machine learning in key industries:

Banking and Finance

Risk management and fraud prevention are key areas where machine learning adds tremendous value in financial contexts.

Healthcare
Diagnostic tools, patient monitoring, and predicting outbreaks are some of the many examples of how machine learning can help improve patient care.

Transportation
Traffic anomaly identification, delivery route optimization, and self-driving cars are examples of ways machine learning can create positive impact in
transportation.

Customer service
Answering questions, gauging customer intent, and providing virtual assistance are examples of how machine learning supports the customer service
industry.

Retail
Machine learning helps retailers analyze buying patterns, optimize offers and pricing, and use data to improve the overall customer experience.

Agriculture
Developing robots to address labor shortages, diagnosing plant diseases, and monitoring the health of the soil are examples of ways machine learning
can improve agriculture. Watch this video to see an example of how machine learning helped increase farmers’ crop yield by 30%.

What to look for in a machine learning platform

When selecting a machine learning platform, look for a solution with the following features:


https://azure.microsoft.com/en-us/resources/cloud-computing-dictionary/what-is-machine-learning-platform/ 5/6
11/6/24, 20:19 What is machine learning? | Microsoft Azure

Cloud computing
Easy to set up and deploy, the cloud is perfect for handling workloads of all sizes, letting you connect data sources and scale on demand—without
requiring advanced knowledge.

Accessible development environment

The ideal platform supports all skill levels with accessible authoring options. It should help you realize the benefits of machine learning whether you
work extensively in code or prefer automated tools and drag-and-drop interfaces that don’t require any coding experience.

Built-in support for familiar machine learning frameworks

Whether it’s ONNX, Python, PyTorch, scikit-learn, or TensorFlow, look for a platform that lets you work with the tools you know and love.

Enterprise-grade security
Look for a platform that comes with enterprise-level governance, security, and control that helps you protect your infrastructure.

Bring your machine learning models to market faster

Simplify the way you build and deploy models with no-code automated
machine learning capabilities, open-source support, and robust DevOps for
machine learning.

Try Azure Machine Learning

Explore Azure Products and Solutions and Partners Resources Cloud computing
pricing support
What is Azure? Azure Marketplace Training and certifications What is cloud computing?
Products Solutions
Get started with Azure Find a partner Documentation What is cloud migration?
Azure pricing Resources for accelerating
Global infrastructure growth Join ISV Success Blog What is a hybrid cloud?
Free Azure services
Datacenter regions Solution architectures Developer resources What is AI?
Flexible purchase options
Trust your cloud Support Students What is PaaS?
Cloud economics
Customer enablement Azure demo and live Q&A Events and Webinars What is IaaS?
Optimize your costs
Customer stories Analyst reports, white What is SaaS?
papers, and e-books
What is DevOps?
Videos

 English (United States) Your Privacy Choices Consumer Health Privacy

Sitemap Contact Microsoft Privacy Terms of use Trademarks Safety & eco Recycling About our ads © Microsoft 2024


https://azure.microsoft.com/en-us/resources/cloud-computing-dictionary/what-is-machine-learning-platform/ 6/6