What is data mining classification?

Data mining classification is one step in the data mining process. It is used to group items based on certain key characteristics. There are several techniques used to classify data mining, including the classification of the nearest neighbor, teaching trees of decision -making and support of vector machines.

Data mining is a method that scientists use to extract patterns from data. In general, a representative sample is selected from the data group and then manipulated and analyzed to find patterns. In addition to data mining classification, scientists can also use clustering, regression and learning rules to analyze data.

There are several algorithms that can be used to classify data mining. The classification of the nearest neighbor is one of the simplest algorithms of data mining. It relies on the training ensemble. Training kit is a set of data used to train your computer until attention to a certain variable. In the classification of the closest neighbor is the computer simply classify allData as part of a group that contains data closest to the input value. The computer basically asks a number of data questions. If the answer to the first question is true, it will ask question 2a. If the answer is false, it will ask the question 2b. When pulling out, this method forms a tree of branch roads.

Naive classification Bayes relies on probability. He asks a number of questions about each piece of data and then uses the answers to determine the probability that the data belongs to a specific classification. This differs from the teaching of the tree decision -making, because the answer to the first question does not affect which question will be further asked.

More complex methods of data mining include neural networks and support vector machines. These methods are computer models that would be difficult to manually. Neuron networks are often used in programming artificial intelligence because it mimics the human brain. Filts the information mediumWith a number of nodes that find patterns and then classify information.

Support vector machines use training samples to create a model that will classify information, usually visualized as a scattering graph with a wide space between categories. When new information is powered into the machine, it is brought into the graph. The data is then classified on the basis of which category the information is closest to the graph. This method only works if you have two options to choose from.