Database Reference
In-Depth Information
Table 12.1 Common Data Mining Algorithms
Algorithm Description
Clustering Rather than a specific algorithm, clustering is a category of
unsupervised algorithms that groups similar objects into
groups or clusters. Typically, a notion of statistical distance
is used to calculate distance between objects. Examples of
these distance calculations include k-means and Euclidean
distance.
Classification Like clustering, classification is not a single algorithm but a
group of algorithms that also group together objects. These
algorithms are usually supervised and require both a
classifier and a training set of data that helps identify what
the groups look like in terms of machine learning. Taken
together, classification algorithms can then classify each
data point or object into the most appropriate group or
bucket.
Regression An outgrowth of statistics, the regression techniques are
used to estimate the relationship between variables.
Regression algorithms such as linear regression are
commonly used for forecasting important business
indicators such as sales volumes.
Association
rules
These algorithms are used to explore or discover
relationships between objects that exist in large data sets.
Common examples of these algorithms include market
basket analysis, clickstream analysis, and fraud detection.
Predictive Analytics
A specialization or subset of the broader data mining field, predictive
analytics (like other forms of data mining) is interested in identifying
patterns. The exception or difference however, is that the patterns identified
are used to make a prediction about some behavior or event using the
historical data fed to the model.
Examples of predictive analytics are everywhere around you. They are used
to determine whether your loan application should be approved, they are
the basis of your credit score, they help recommend what movie you should
 
Search WWH ::




Custom Search