The nPath function scans a set of rows, looking for patterns that you specify. For each set of input rows that matches the pattern, nPath produces a single output row. The function provides a flexible pattern-matching capability that lets you specify complex patterns in the input data and define the values that are output for each matched input set.
nPath is useful when your goal is to identify the paths that lead to an outcome. For example, you can use nPath to analyze:
- Web site click data, to identify paths that lead to sales over a specified amount
- Sensor data from industrial processes, to identify paths to poor product quality
- Healthcare records of individual patients, to identify paths that indicate that patients are at risk of developing conditions such as heart disease or diabetes
- Financial data for individuals, to identify paths that provide information about credit or fraud risks
The output from the nPath function can be input to other ML Engine functions or to a visualization tool such as Teradata AppCenter.
Sankey Diagram of ML Engine nPath Output
An nPath call specifies: