Predictive scores help you to identify high intent vs low intent customers. After you have set up the predictive scores, the next step is to create a targeted segment to increase your campaign performance.
If your existing campaigns are targeting a large customer base, you can use the predictive scores to filter your audience to target a subset of customers and increase the performance of your campaign.
To measure the conversion attribution, create a control group based on bsft_control_bucket and test it against customer groups based on predictive scores.
In this campaign we are targeting 4 groups of customers:
- Control group - Use the bsft_control_bucket attribute to create a control group. Customers with bsft_control_bucket 0-25 are part of this group and represent 25% of the customer base.
- Group 1 - Low intent customers with a purchase score of 0-33.
- Group 2 - Mid intent customers with a purchase score of 34-66.
- Group 3 - High intent customers with a purchase score of 67-100.
Once the campaign is launched the metrics for each vertical branch can be compared to see the efficacy of different deciles vs control group.