Setup and Activation
How can we enable the Attribute Affinity for the product attributes?
You can enable Affinity Modeling by navigating to Components > Product Catalog Management > Product Attributes.
How soon can we start using Discount Affinity after activating it?
Insider recommends having at least one month of data after enabling the data collection.
Data Requirements
What is the lowest limit of data for eligibility for using the Predictive Segments?
To run the algorithms below, you will need the required event numbers and product quantities.
Likelihood to Purchase: The required product page view count should be above 1000. Success events must be equal to or above 100 in 7 days, and the algorithm should run for at least 14 days.
User Engagement: Both Likelihood to Open and Likelihood to Engage algorithms should be running for all channels.
To run the Likelihood to Open algorithm for Email, you should run the algorithm for at least 30 days with at least 1000 email-delivered events, at least 100 email open events, and at least 10 email click events.
To run the Likelihood to Engage algorithm for SMS, you need at least 100 sms click events in 7 days and at least 1000 sms delivered events in 7 days.
To run the Likelihood to Engage algorithm for Web Push, you should run the algorithm for at least 21 days. The total page view event count should be above 1000 in 7 days, the Web Push click event count should be above 100 in 7 days, and the Web Push view event count should be above 1000 in 7 days.
To run the Likelihood to Engage algorithm for WhatsApp, the required WhatsApp click event count should be at least 100 in 7 days, and the WhatsApp delivered event count should be at least 1000 in 7 days.
To run the Likelihood to Engage algorithm for App Push, the following conditions must be met: a total of at least 1000 page views and push delivered events, at least 100 push sessions on events, and the algorithm must run for a minimum of 21 days.
Customer Lifecycle Status: The required purchase event view count should be above 100.
Discount Affinity: The required product page view count should be at least 1000. The purchase event view and discounted items should be above 100, and the algorithm should run for at least 14 days.
Attribute Affinity: The required product page view event count should be above 100, and the products with attribute event count should be above 100.
What is the data span for the Customer Lifecycle Status algorithm?
Insider uses one year of data. Let's take a brand for which Insider has collected data for two years. This brand uses Insider tracking with the same cookie for two years. Their last purchase was one and a half years ago, but they have visited the website since then. This user is not classified as a buyer because Insider considers only the last year of data. That's why this user will be within one of the non-buyer segments.
What is the data span for Discount Affinity?
The algorithm uses the last 6 months' data (180 days).
Algorithm Behavior and Limitations
Can we keep track of a buyer user's activities if they delete their cookies?
Data collection is limited to cookies. If a user clears their cookies, they are considered new users unless they are logged in. Only logged-in users are unified in Insider's database based on their email address and can be tracked regardless of their cookie ID.
Campaign and Audience Management
How can I create a campaign for one-time purchasers?
You should select the Customer Lifecycle Status as Active and the Purchase Count (all-time) as equal to 1.
Why don't users see the campaign even though I've selected the predictive segment for my Web Templates campaign?
Predictive segments have prerequisites for use. If the algorithm is not ready yet, you cannot use the related segment. In such cases, these segments appear locked and cannot be selected in campaigns. However, Onsite products have a separate segment page, and the segments do not appear as locked as they do with other products. As a result, even if you select this segment for a campaign, the campaign might not be visible to users because the algorithm isn't ready.
What is the average size of the Likelihood to Purchase audience?
It is around 5-15% of the total audience (number of events/number of users for a given date range).
Industry Specific Usage
Our business is not an ecommerce. Can we use the Discount Affinity?
No, the Discount Affinity algorithm is only for ecommerce businesses.
Can any industry use Likelihood to Purchase?
As the key identifier in the Likelihood to Purchase algorithm is purchase, it is recommended for the ecommerce verticals.