20.11.2015 Views

Data Mining Extensions - DMX - Reference

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Bike Buyer Bike Buyer = Yes Bike Buyer = No<br />

1 0.867074195848097 0.132755556974282<br />

See Also<br />

<strong>Data</strong> <strong>Mining</strong> Functions <strong>Reference</strong>)<br />

Functions (<strong>DMX</strong>)<br />

Mapping Functions to Query Types (<strong>DMX</strong>)<br />

PredictSequence<br />

Predicts future sequence values for a specified set of sequence data.<br />

Syntax<br />

PredictSequence()<br />

PredictSequence()<br />

PredictSequence()<br />

Return Type<br />

A .<br />

Remarks<br />

If the n parameter is specified, it returns the following values:<br />

• If n is greater than zero, the most likely sequence values in the next n steps.<br />

• If both n-start and n-end are specified, the sequence values from n-start to n-end.<br />

Examples<br />

The following example returns a sequence of the five products that are most likely to be<br />

purchased by a customer in the Adventure Works DW Multidimensional 2012<br />

database based on the Sequence Clustering mining model.<br />

SELECT<br />

PredictSequence([Sequence Clustering].[v Assoc Seq Line Items],5)<br />

From<br />

[Sequence Clustering]<br />

See Also<br />

Mapping Functions to Query Types (<strong>DMX</strong>)<br />

Functions (<strong>DMX</strong>)<br />

Mapping Functions to Query Types (<strong>DMX</strong>)<br />

121

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!