DATABASE TECHNOLOGY

Database Technology

Section A

Data Mining

The data mining concerns the extraction of knowledge or knowledge from large amounts of data (through automatic or semi-automated methods) and the industrial use or operation of this knowledge. The use of data mining in market research intends to broaden the knowledge on which to base decisions. In the business context of data mining, it is considered part of the process leading to the creation of a data warehouse. It is especially effective for the enhancement of corporate information residing in these large stores of data. Ensure that the information extracted from existing data is significant and potentially useful, it must be: (Dulli, 2009, 47).

valid (that can also act on new data);

previously unknown;

Understandable.

In this context, a pattern (explanation) is just the representation of the key relationships that are discovered during the process of extracting data: repeated sequences, homogeneity, emergency rules, etc. For example, if a pattern shows that customers of a certain demographic area are very likely to buy a specific product, then a query to a selective data warehouse of likely buyers can be used to generate a list of addresses promotions. The concept of data mining is similar. The only difference is that this new discipline has to do with substantial data sets. In essence, data mining is the ' mathematical analysis performed on the database of large size. “The term data mining has become popular in the late 90's as a shortened version of the definition set out above (Dulli, 2009, 47).

Data mining has led to a gradual replacement of data analysis. The data mining techniques are being used for several years to obtain patterns in data and to extract valuable information in the field of Software Engineering. Data mining is the science of extracting useful information from large data sets or databases. It is used to create empirical models, which are not based on the principles of operation of the process or mechanism underlying data, but rather on data from the observation process. It provides a description of observed data. It essentially aims for the better understanding of the data structure and its important features, and to discover and extract patterns from data sets.

Today, data mining (literally, data mining, has a double meaning:

Extraction, with advanced analytical techniques, implicit information, hidden from data already structured to make it available and directly usable;

Exploration and analysis, carried out automatically or semi-automatic, large amounts of data in order to discover patterns (patterns) significant.

In both cases, the concepts of information and meaning are closely related to the application domain in which one performs data mining, in other words, an item may be interesting or negligible depending on the type of application in which you want to operate. This type of activity is crucial in many areas of scientific research, but also in other sectors (e.g. that of market research). In the professional world is used to solve different problems with each other, ranging from customer relationship management (CRM), detection of fraudulent behaviour to finish the optimization of ...