**3.3 Data mining techniques and tasks**

Understanding the types of tasks, or problems, that data mining can solve is the best way to learn about it. The majority of data mining tasks can be classified as either prediction or summary at a high level. Predictive tasks allow you to forecast the value of a variable based on previously collected data. Predicting when a customer will leave a business, predicting whether a transaction is fraudulent, and recognizing the best customers to receive direct marketing offers are all examples of predictive tasks. Descriptive tasks, on the other hand, attempt to summarize the information. Automatically segmenting customers based on their similarities and differences, as well as identifying correlations between products in market-basket data, are examples of such tasks [12].

Organizations now have more data at their disposal than they have ever had before. However, due to the sheer volume of data, making sense of the massive amounts of organized and unstructured data to enact organization-wide changes can be exceedingly difficult. This problem, if not properly handled, has the potential to reduce the value of all the data.

Data mining is the method by which businesses look for trends in data to gain insights that are important to their needs. Both business intelligence and data science need it. Organizations may use a variety of data mining strategies to transform raw data into actionable insights [13]. These range from cutting-edge artificial intelligence to the fundamentals of data planning, all of which are critical for getting the most out of data investments.


*The Concept of Data Mining DOI: http://dx.doi.org/10.5772/intechopen.99417*


Cleaning and preparing data is a vital part of the data mining process. Raw data must be cleansed and formatted in order to be useful in various analytic approaches. Different elements of data modeling, transformation, data migration, ETL, ELT, data integration, and aggregation are used in data cleaning and planning. It's a necessary step in determining the best use of data by understanding its basic features and attributes. Cleaning and preparing data has obvious business value. Data is either useless to an entity or inaccurate due to its accuracy if this first phase is not completed. Companies must be able to trust their data, analytics results, and the actions taken as a result of those findings. These measures are also needed for good data quality and data governance.

b.Pattern Recognition

A basic data mining technique is pattern recognition. It entails spotting and tracking trends or patterns in data in order to draw informed conclusions about business outcomes. When a company notices a pattern in sales data, for example, it has a reason to act. If it's determined that a certain product sells better than others for a specific demographic, a company may use this information to develop similar goods or services, or simply better stock the original product for this demographic [14].

c.Classification

The various attributes associated with different types of data are analyzed using classification data mining techniques. Organizations may categorize or classify

similar data after identifying the key characteristics of these data types. This is essential for recognizing personally identifiable information that organizations may wish to shield or redact from records, for example.
