Journey Discovery - Introduction and Considerations
This page provides a general overview of Journey Discovery, as well as some very important guidelines, assumptions and considerations in the following areas:
Ensure the correct Data Capture required prior to execution
Consider the length of Journey Journeys to drive Journey Discovery date range selection
Ensure a Data Transform has been agreed and published (Admins only)
Ensure a Location Map has been created
Considerations for the approach to Journey Discovery
Journey Discovery Overview
When Alterian CX collects Location data of interaction points by Visitors/Customers to the Brand, these can be viewed in either multi-channel sessions (Interactions), or a Visitor/Customers entire interaction history using the existing Journey Visualisation Sankey diagram. In this display, these sequence paths are overlaid with each other, to show the most common occurring behaviours.
Journey Visualisation allows the analyst to left align, or right align the Journey Visualisation view to focus on what happens before or after a specific Location, and this can be very powerful, but only when the Analyst knows the interactions they are interested in.
The Journey Discovery process uses machine learning and data mining functions to analyse the multi-channel sessions (Interactions) and find patterns or “Micro Journeys” of Locations that are occurring in the Interaction data, that the Analyst may not be aware of.
Using Journey Discovery requires a number of items or processes to be in place prior to its use. Journey Discovery should not be carried out without ensuring the following has been done.
Capture the Correct Data Required for Analysis- See below
Have a Period of Data Collection to the Production Event Stream - See below
Create and assign an agreed Data Transform to the Event Stream - https://alteriandocs.atlassian.net/wiki/spaces/PD/pages/1781628935
Create and publish an agreed Location Map to the Event Stream - https://alteriandocs.atlassian.net/wiki/spaces/PD/pages/1801289729
Capture the Correct Data Required for Analysis
IMPORTANT NOTE: In terms of data collection, this is reliant on the implementation of the system within the Brand, from tagging or other data connectors, through to the creation of Rules within Alterian CX and is therefore may not be under the control of the Analyst. Failure to review this section, and collect the full range of data, will significantly reduce the insights that could be gleamed from Journey Discovery for the Analyst so shortfalls in data should be flagged.
The bullets below outline each data point required and its use within the Journey Discovery process and is therefore of paramount importance.
CXID
Internally created id used within Alterian CX for Analysis
Location
Location data must be of the highest quality and have a published and agreed Data Transform to ensure the Locations values passed to Journey Discovery are appropriate for the Analyst to view and understand. See https://alteriandocs.atlassian.net/wiki/spaces/PD/pages/1781628935
Category
Although not mandatory for Journey Discovery, Category can be very useful in future analytics on the discovered patterns
Event Type
Event Type is collected and associated to the Rule type
Tracking
Conversion
Influencer
Satisfaction
Event DateTime
Internally created Event DateTime used within Alterian CX for Analysis
Channel
This must include all Channels that are used in the Journeys
Conversion Value
Conversions should be captured when a monetary value can be ascribed to a Conversion
Conversion value captured on Conversion Event Type only
Required for the Stats Analysis of Micro Journeys and Journeys
Service Cost
Service Costs should be captured when a monetary cost can be ascribed to an interaction
Service Cost can be captured on any Event Type
Required for the Stats Analysis of Micro Journeys and Journeys
For more information on the data capture see CX Data Analytics Event History Schema
A Period of Data Collection to the Production Event Stream
Journey Discovery is only going to be of value if it performed if it contains the correct data for the correct period of time. In terms of the required time period for data collection, if the Analyst is looking for a range of all Journeys, the Brand must first consider how long these Journeys are in the real world. For example, a Finance Company wanting to view their Journeys around Mortgages or Loans, must consider the time taken for their Customers to complete these Journeys or as an absolute minimum, how long each stage takes and ensure there is enough Customer data that every stage will be well represented in the data.
Creation and publication on an agreed Data Transform
Data Transform is a very important function in the use of all CX Analytics
https://alteriandocs.atlassian.net/wiki/spaces/PD/pages/1781628935
Creation of a Location Map
Data Transform is a very important function in the use of all CX Analytics
https://alteriandocs.atlassian.net/wiki/spaces/PD/pages/1801289729
Saving Journey Discovery Result Sets
Once initially created, Journey Discovery executions auto-save in the last known state. States of execution can be seen on the Journey Discovery homepage as follows
Initialised - New Journey Discovery created but with no configuration
Prepared - A date range has been selected and a data set prepared
Calculated - The Micro Journey discovery process is compete but results have not been scored or uploaded to the result screen
Uploaded - Journey Discovery process is complete and results can be viewed
Results Persistence
A Journey Discovery result, is based on its defined components, related to execution of the process against a specified Event Stream/Target.
Each execution of a Journey Discovery process will persist, save and re-use its component parts
Date Range - Selects the data set that s built in the “preparing” section (see usage)
Execution Parameters - Available parameters to guide the machine learning function
Data Transform - the version of the Data Transform set and fixed at start of process
Location Map - the version of the Location Map set and fixed at start of process
Journey Ranking - Ranked list of Journeys created via Location Map, in terms of required focus for scoring.
For next steps see Journey Discovery - User Guide & Journey Discovery - Approach to Analytics