Choosing an Algorithm by Task

 

 

Choosing an Algorithm by Task

To help you select an algorithm for use with a specific task, the following table provides suggestions for the types of tasks for which each algorithm is traditionally used. +

Examples of tasks

Microsoft algorithms to use

Predicting a discrete attribute:

 

Flag the customers in a prospective buyers list as good or poor prospects.

 

Calculate the probability that a server will fail within the next 6 months.

 

Categorize patient outcomes and explore related factors.

Microsoft Decision Trees Algorithm

 

Microsoft Naive Bayes Algorithm

 

Microsoft Clustering Algorithm

 

Microsoft Neural Network Algorithm

Predicting a continuous attribute:

 

Forecast next year's sales.

 

Predict site visitors given past historical and seasonal trends.

 

Generate a risk score given demographics.

Microsoft Decision Trees Algorithm

 

Microsoft Time Series Algorithm

 

Microsoft Linear Regression Algorithm

Predicting a sequence:

 

Perform clickstream analysis of a company's Web site.

 

Analyze the factors leading to server failure.

 

Capture and analyze sequences of activities during outpatient visits, to formulate best practices around common activities.

Microsoft Sequence Clustering Algorithm

Finding groups of common items in transactions:

 

Use market basket analysis to determine product placement.

 

Suggest additional products to a customer for purchase.

 

Analyze survey data from visitors to an event, to find which activities or booths were correlated, to plan future activities.

Microsoft Association Algorithm

 

Microsoft Decision Trees Algorithm

Finding groups of similar items:

 

Create patient risk profiles groups based on attributes such as demographics and behaviors.

 

Analyze users by browsing and buying patterns.

 

Identify servers that have similar usage characteristics.

Microsoft Clustering Algorithm

 

Microsoft Sequence Clustering Algorithm

Related Content

The following table provides links to learning resources for each of the data mining algorithms that are provided in SQL Server Data Mining: +

Basic algorithm description

Explains what the algorithm does and how it works, and outlines possible business scenarios where the algorithm might be useful.

 

Microsoft Association Algorithm

 

Microsoft Clustering Algorithm

 

Microsoft Decision Trees Algorithm

 

Microsoft Linear Regression Algorithm

 

Microsoft Logistic Regression Algorithm

 

Microsoft Naive Bayes Algorithm

 

Microsoft Neural Network Algorithm

 

Microsoft Sequence Clustering Algorithm

 

Microsoft Time Series Algorithm

Technical reference

Provides technical detail about the implementation of the algorithm, with academic references as necessary. Lists the parameters that you can set to control the behavior of the algorithm and customize the results in the model. Describes data requirements and provides performance tips if possible.

 

Microsoft Association Algorithm Technical Reference

 

Microsoft Clustering Algorithm Technical Reference

 

Microsoft Decision Trees Algorithm Technical Reference

 

Microsoft Linear Regression Algorithm Technical Reference

 

Microsoft Logistic Regression Algorithm Technical Reference

 

Microsoft Naive Bayes Algorithm Technical Reference

 

Microsoft Neural Network Algorithm Technical Reference

 

Microsoft Sequence Clustering Algorithm Technical Reference

 

Microsoft Time Series Algorithm Technical Reference

Model content

Explains how information is structured within each type of data mining model, and explains how to interpret the information stored in each of the nodes.

 

Mining Model Content for Association Models (Analysis Services - Data Mining)

 

Mining Model Content for Clustering Models (Analysis Services - Data Mining)

 

Mining Model Content for Decision Tree Models (Analysis Services - Data Mining)

 

Mining Model Content for Linear Regression Models (Analysis Services - Data Mining)

 

Mining Model Content for Logistic Regression Models (Analysis Services - Data Mining)

 

Mining Model Content for Naive Bayes Models (Analysis Services - Data Mining)

 

Mining Model Content for Neural Network Models (Analysis Services - Data Mining)

 

Mining Model Content for Sequence Clustering Models (Analysis Services - Data Mining)

 

Mining Model Content for Time Series Models (Analysis Services - Data Mining)

Data mining queries

Provides multiple queries that you can use with each model type. Examples include content queries that let you learn more about the patterns in the model, and prediction queries to help you build predictions based on those patterns.

 

Association Model Query Examples

 

Clustering Model Query Examples

 

Decision Trees Model Query Examples

 

Linear Regression Model Query Examples

 

Logistic Regression Model Query Examples

 

Naive Bayes Model Query Examples

 

Neural Network Model Query Examples

 

Sequence Clustering Model Query Examples

 

Time Series Model Query Examples

Related Tasks

Topic

Description

Determine the algorithm used by a data mining model

Query the Parameters Used to Create a Mining Model

Create a Custom Plug-In Algorithm

Plugin Algorithms

Explore a model using an algorithm-specific viewer

Data Mining Model Viewers

View the content of a model using a generic table format

Browse a Model Using the Microsoft Generic Content Tree Viewer

Learn about how to set up your data and use algorithms to create models

Mining Structures (Analysis Services - Data Mining)

 

Mining Models (Analysis Services - Data Mining)

 

IT partner ecosystem
EMC2Data partners with an extensive ecosystem of innovative organizations to offer powerful tools to support your digital business initiatives.