Autosegments

Autosegmentation uncovers hidden opportunities for marketers by automatically generating high-value segments. Using AI to find unique combinations of customer properties and metrics, Autosegments remove the effort needed to analyze data and build hyper-targeted segments manually.

By targeting a more valuable micro-segment, marketers can expect to increase conversions within their campaign, driving first-time or repeat purchases. Marketers can also tailor the content and recommended products within a campaign based on the qualitative insights about a segment provided by Autosegments.

How do Autosegments work

Autosegments are powered by Loomi, our AI, to generate potential segments from unique combinations of customer properties and metrics.

Potential segments are presented using a visual, interactive chart that supports further exploration. Marketers can click into each segment for quantitative and qualitative insights, such as a favorite category, average order value, or revenue per visitor, allowing them to pick the best one and create it with a click to use in a personalized campaign.

Segments created via the Autosegments feature can be immediately used like any audience segment within Bloomreach Engagement - in Scenarios, Campaigns, Reporting, and more.

πŸ“˜

Autosegments is currently available only to selected customers

Autosegments is only available to selected Engagement customers, upon approval from the Bloomreach team. If you’re interested in gaining access, please reach out to your Customer Success Manager or Account Manager.

How to create and implement Autosegments

πŸ“˜

Requirements

  • You must enter at least one customer property and at least 2 metrics.
  • You must have existing customer properties and metrics before using them in Autosegments. Learn how to define properties here and create metrics here.

1. Create new Autosegment

Go to Analyses > Autosegments and click on + New autosegment.

Choose a predefined use case in the form of a template or create a new autosegment from scratch. You can also leave feedback if an important template is missing.

If you select one of the existing templates, the following user experience is the same as when selecting a use case from the Use Case Center.

2. Define your values

Select customer properties and metrics on which you wish our AI to base the Autosegments.

You can use a maximum of:

  • 20 properties
  • 10 metrics
  • 5000 segments (if more segments are generated, a random subset is returned)
  • last 12 months of data

πŸ“˜

Segments are mutually exclusive

Each segment within Autosegments feature operates independently, and does not influence another segment in any way. This allows the segments to consider all combinations of properties and filters.

3. Save and start your autosegment

Click on Save and then Start to generate Autosegment. You can see the process in the Results tab. It can take up to 24 hours to generate your Autosegment. The metrics are calculated while running the Autosegment and are not recalculated in real-time when working with Autosegment results.

πŸ“˜

Only segments that meet the defined 'Minimum user count for each segment' are returned as a result.

4. View and analyze the generated Autosegment

Once the Autosegment is generated, you can see the results in the Results tab.

The result is presented as a table with all the segments. The table could be sorted according to the metrics. The segments could also be filtered based on the metrics. The result is also visualized in the form of a diagram.

Click on any segment, either in the table or the diagram, and open a modal window with the segment details:

  • segment name
  • segment description: detail about used properties and values, portion from all customers (100% of customers is the number of customers after applying the customer filter from the setup screen)
  • metrics for the specific segment compared to overall project performance
  • action button: create segment - this opens a new definition of segmentation with one segment based on the clicked one

πŸ“˜

Reading the segment metrics table

Please note the metrics in the segment table present values for the whole customer base within the particular segment. For example, the average customer lifetime value in the table above (avg_cltv = 48.64) demonstrates the value of the whole customer base within the Segment 177 (averaging the lifetime value of 33,753 customers), and not a value pertaining to each customer individually.

5. Create a segmentation

Choose the segment(s) that you find useful and create a new segmentation. You can then use this segmentation to personalize marketing campaigns or optimize your product offerings.

Use case examples

The basic scenario is finding a relevant segment that needs to be treated in some special way. Whether it is to support the segment to increase engagement or not to waste resources on some underperforming segments.

Example 1 - email campaign optimization:

Run the Autosegmetns with the following setup:

  • properties: most visited category level 1, most visited category level 2, gender, interest in flash sales, last device type, country, age
  • metrics: CLTV, email click-through rate, conversion rate

As a result, you see many different segments, but when you sort them based on the email click-through rate, some underperforming segments appear. Click on it and also see that the CLTV is above average. This means that this segment is important for you but also underperforming in terms of email campaigns. Based on the segment details (e.g., seeing that the segment consists of young people visiting from mobile devices and mainly visiting some specific category), a marketer could decide to approach the segment with different content and maybe even through a different channel (e.g., mobile notification).

Looking at the chart, the marketer can see the relationship between importance (vertical axis) and email performance (horizontal axis) together with the size of the segment (bubble size). So, the bottom left quadrant is where the marketer focuses and identifies segments to which the campaign could be better personalized next time.

Example 2 - paid traffic optimization:

Run the Autosegmetns with the following setup:

  • properties: most visited category, gender, interest in flash sales, RFM
  • metrics: revenue per visitor (RPV), traffic % from paid channels, revenue per buyer, conversion rate

As a result, you can see many different segments, but when you sort them based on the RPV, some quite underperforming segments appear. When you click on it, you also see that the 'traffic % from paid channels' is quite high.

From a business perspective, this means, that you invest a lot into this segment, but you are not getting the value back. The action step could be to exclude such segments from retargeting or change the overall retargeting settings to exclude such segments.