What Is Data Mining?

Written by Coursera Staff • Updated on

Learn more about data mining, including how it works, the different data mining techniques, and the role of machine learning in data mining.

[Featured Image] A digital marketer sits at a laptop and uses data mining to analyze customer behavior.

In order for raw data to become useful information that you can then analyze to help make important decisions, it first goes through a multistep process known as data mining. Data mining has applications in numerous industries, including manufacturing, education, health care, technology, media, banking, and more. In addition to serving several industries, data mining is a regular task you will perform in a career in data science and business analytics.

What is data mining?

Data mining is the process, or technique, of discovering information in large sets of data, such as patterns and relationships, that you can then use to make informed decisions. This process happens with the help of computers and automated processes made possible through artificial intelligence and machine learning. Data mining follows a specific process, beginning with a question of what the objective is and ending with insights that contribute to developing strategies.

Why data mining is important

After establishing trends in the data through data mining, you have the ability to leverage that information to acquire more customers, make business operations more efficient, and better understand your consumers. Every industry can benefit from data mining, as it has applications within medical diagnosis, price optimization, risk assessment, and fraud detection, among many others.

How data mining works

The cross-industry standard process for data mining (CRISP-DM) is a six-step process and the industry standard for data mining. Let's take a look at what you can expect in each stage.

1. Business understanding

The data mining process starts with a problem you’re attempting to solve or a specific objective for the project. Understanding the goals in mind is important to ensure the correct, relevant data sets are the ones you’re analyzing. 

2. Data understanding

Step two is the collection of all the relevant data, which includes ensuring the data is complete, without duplicates, and typically from multiple sources.

3. Data preparation

During data preparation, you are putting the data into its proper format so that it’s ready to go through analysis and transfer over to the database for use. The three sub-steps of data preparation are extraction, transformation, and loading, commonly called ETL.

4. Modeling

During modeling, the data goes through different data mining techniques and tools, and the right model or models is selected depending on the data and your objective. These techniques include clustering, regression analysis, and classification.

5. Evaluation

The question or initial objective you previously established in step one should now have an answer. But if not, then you return to the previous step of modeling and make any necessary adjustments to the data.

6. Deployment

Before moving on to deployment, it’s important the data modeling process gives you answers to your objective. Once you have these answers, you can present and use the information strategically. 

Data mining techniques

You will use a variety of different strategies to find insights within data sets. Here’s a closer look at several data mining techniques:

  • Clustering: Grouping similar data points together is clustering. Ultimately, data that goes through clustering is divided into subgroups. You can use these subgroups further as input data for other data mining techniques.

  • Classification: Classification also splits data sets up into smaller groups. Classification is a common yet complex technique where the model searches for data points with similarities to help predict outcomes.

  • Association rule: The association rule technique shows the probability of a relationship between a pair of unrelated datasets. One example where you see this technique in practice is suggesting a certain item to a customer based on previous purchases.

  • Regression analysis: Regression is a more mathematical-based technique that helps you understand the most important factors within a data set and how they interact, ultimately enabling you to make accurate forecasts and predictions.

  • Outlier detection: Outlier detection is important for spotting potential errors in the data set, as well as unique data worth taking a closer look at in order to understand the outlier. 

Machine learning and data mining

Machine learning is an area of artificial intelligence where you train computers to analyze data to spot patterns and trends. You accomplish this by developing algorithms and training them with large amounts of data in order to learn to make predictions. 

Data mining plays an important role in machine learning as machine learning implements data mining to identify trends found in the data and use these trends to train predictive models. Machine learning is also capable of supporting certain data mining techniques. For example, you can use machine learning algorithms to convert unstructured data into structured data to make the information more easily usable for data mining. Other parts of the data mining process that can benefit from machine learning are data cleaning, entry, and removing duplicate information. Machine learning algorithms have the ability to automate these processes.

Data mining careers

Data mining is part of the job responsibilities for careers within data science and data analytics. It is an important skill to possess for positions handling big data. Sometimes, a company may hire a data mining specialist to help with artificial intelligence and machine learning scripting. Here’s a look at three data mining-related careers:

Data scientist

Median annual US salary (Glassdoor): $129,767 [1]

As a data scientist, you will help your organization collect and analyze data and develop insights from the data using predictive models, algorithms, and data models. With this information, organizations can solve problems and make informed decisions. This position requires computer programming, machine learning, and statistical analysis skills.

Market research analyst

Median annual US salary (Glassdoor): $70,227 [2]

As a market research analyst, you will use data about your customers and market conditions to develop marketing strategies. Your responsibilities include analyzing large data sets, monitoring the performance of your marketing strategies, and performing market research. 

Data analyst 

Median annual US salary (Glassdoor): $76,995 [3]

As a data analyst, you will collect and analyze data. This develops insights that you can use for important business decisions, such as how to better meet your customers' needs. Data analysts have skills in data visualization, programming, and statistical analysis.

Getting started with Coursera

On Coursera, you can find highly rated courses to learn more about data mining, data science, and analytics. The Data Mining Specialization from the University of Illinois at Urbana-Champaign is a great option for learning about text mining, data mining, data visualization, and more.

The Data Science Specialization from Johns Hopkins University is another great option to develop your data science skills further. This course covers practical machine learning applications and regression analysis models. 

Article sources


Glassdoor. “How much does a data scientist make?, https://www.glassdoor.com/Salaries/data-scientist-salary-SRCH_KO0,14.htm.” Accessed March 4, 2024.

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.