Path Analysis Functions - Teradata Vantage

Machine Learning Engine Analytic Function Reference

Product
Teradata Vantage
Release Number
8.00
1.0
Published
May 2019
Language
English (United States)
Last Update
2019-11-22
dita:mapPath
blj1506016597986.ditamap
dita:ditavalPath
blj1506016597986.ditaval
dita:id
B700-4003
lifecycle
previous
Product Category
Teradata Vantageā„¢

The path analysis functions automate path analysis. They are useful for clickstream analysis of web site traffic and other sequence/path analysis tasks, such as advertisement or referral attribution.

Terms Function Descriptions Use

Term Definition
Path Ordered, start-to-finish series of actions, such as the page views of a user from the start to the end of a session. For example, if the user visits page a, page b, and page c, in that order, the path is: a,b,c
Sequence Path in this format:
^,path

The carat (^) indicates that a path follows. For example: ^,a,b,c

Subsequence or prefix For a given sequence, a possible subset of steps that start with the initial step. For example, for the path a,b,c these are the subsequences:
^,a
^,a,b
^,a,b,c
Exit subsequence or prefix Subsequence or prefix that is the same as its sequence, indicated by a final dollar sign ($). For example: ^,a,b,c$
Depth Number of steps in a sequence or subsequence. For example, the immediately preceding subsequences have depths 1, 2, and 3, respectively.
Node Single step on a path. For example, one web page that the user visits during the session.
Parent Path the user traveled to a given node. For example, the parent of c is: ^,a,b
Child Path the user traveled from a given node. For example, these are the children of ^,a:
^,a,b
^,a,b,c

Path Analysis Functions

Function Description
PathGenerator Takes a set of paths and outputs the sequence and all possible subsequences.
PathSummarizer Takes PathGenerator output and returns, for each prefix in the input table, the parent and children, and number of times each of its subsequences was traveled.
PathStart Takes PathGenerator output and returns, for each parent in the input table, the parent and children and the number of times that each of its subsequences was traveled.
PathAnalyzer Runs the preceding path analysis functions in the order shown, using the output of PathGenerator as input to PathSummarizer and the output of PathSummarizer as the input to PathStart.