Overview
While creating an A/B activity using the three-step guided workflow, choose the Auto-Target for personalized experiences option on the Targeting page (step 2).
The Auto-Target option within the A/B activity flow lets you harness machine-learning to personalize based on a set of marketer-defined experiences in one click. Auto-Target is designed to deliver maximum optimization, compared to traditional A/B testing or Auto Allocate, by determining which experience to display for each visitor. Unlike an A/B activity in which the objective is to find a single winner, Auto-Target automatically determines the best experience for a given visitor. The best experience is based on the visitor’s profile and other contextual information to deliver a highly personalized experience.
Similarly to Automated Personalization, Auto-Target uses a Random Forest algorithm, a leading data science ensemble method, to determine the best experience to show to a visitor. Because Auto-Target can adapt to changes in visitor behavior, it can run perpetually to provide lift. This method is sometimes referred to as “always-on” mode.
Unlike an A/B activity in which the experience allocation for a given visitor is sticky, Auto-Target optimizes the specified business goal over each visit. Like in Auto Personalization, Auto-Target, by default, reserves part of the activity’s traffic as a control group to measure lift. Visitors in the control group are served a random experience in the activity.
Considerations
There are a few important considerations to keep in mind when using Auto-Target:
-
You cannot switch a specific activity from Auto-Target to Automated Personalization, and the opposite way.
-
You cannot switch from Manual traffic allocation (traditional A/B Test) to Auto-Target, and the opposite way after an activity is saved as draft.
-
One model is built to identify the performance of the personalized strategy versus randomly served traffic versus sending all traffic to the overall winning experience. This model considers hits and conversions in the default environment only.
Traffic from a second set of models is built for each modeling group (AP) or experience (AT). For each of these models, hits and conversions across all environments are considered.
Requests are served with the same model, regardless of environment, but the plurality of traffic should come from the default environment to ensure that the identified overall winning experience is consistent with real-world behavior.
-
Use a minimum of two experiences.
Terminology
The following terms are useful when discussing Auto-Target:
Term | Definition |
---|---|
Multi-armed bandit | A multi-armed bandit approach to optimization balances exploratory learning and exploitation of that learning. |
Random Forest | Random Forest is a leading machine learning approach. In data-science speak, it is an ensemble classification, or regression method, that works by constructing many decision trees based on visitor and visit attributes. Within Target, Random Forest is used to determine which experience is expected to have the highest likelihood of conversion (or highest revenue per visit) for each specific visitor. |
Thompson Sampling | The goal of Thompson Sampling is to determine which experience is the best overall (non-personalized), while minimizing the “cost” of finding that experience. Thompson sampling always picks a winner, even if there is no statistical difference between two experiences. |