"Bi thing" Microsoft sequential analysis and clustering algorithm

In the original: "Bi thing" Microsoft sequential analysis and clustering algorithm

The Microsoft Sequential Clustering algorithm is a sequential parsing algorithm provided by Microsoft SQL Server Analysis Services. You can use this algorithm to study data that contains events that can be linked by the following path or "order". The algorithm finds the most common order by grouping or classifying the same order. Here are some examples of the order:

• Used to describe the data of the click path that the user generated when navigating or browsing the site.
• Data that is used to describe the order in which customers add items to an online retailer's shopping cart.

The algorithm is similar to the Microsoft clustering algorithm in many ways. However, the Microsoft sequential clustering algorithm does not look for clusters that contain cases of similar attributes, but rather finds clusters of cases with similar paths in the order.

Example
The Adventure Works Cycles site collects information about which pages a site user accesses and the order in which they are accessed. Because the company provides online ordering, users must log on to this site. This can provide click-through information for each of the company's customer profiles. By using the Microsoft sequence Clustering algorithm for this data, the company can find customer groups or categories that have the same click mode or click Order. The company can then use these classifications to analyze how users move around the site to identify which pages are most closely related to a particular product and predict which pages are most likely to be accessed next.

Here we go to the topic, through a simple process configuration we can implement the entire data mining process, followed by the following steps:

Reference documents:

Microsoft sequential analysis and clustering algorithms
http://msdn.microsoft.com/zh-cn/library/ms175462 (v=sql.105). aspx

"Bi thing" Microsoft sequential analysis and clustering algorithm