Heap Analytics

Analytics Platforms

Heap Analytics is a web analytics tool that allows you to capture and measure every user action on your website or mobile app including clicks, taps, swipes, page views, form submissions, and more.

Heap Analytics

Black Crow will send unique information about the user and their score as a User Property into your heap.io platform on your behalf. To run an analysis on your users, please see Heaps documentation here.

Please notify your Account Manager, who can help get this enabled for you.


Helpful information for your Analyst:

Black Crow generates real-time predictions of how likely users are to achieve a specific action (typically purchase) in the future.

Inside Heap, the user property for Black Crow looks something like BlackCrow|site|3 with a value of 2

The structure of the key in the user profile is made up of three parts separated by a pipe |

  • Vendor name: A hardcoded static string BlackCrow to help label what is being set by Black Crow
  • Comparison group: A dynamic field that is either site, page or some other custom value that a Black Crow team member will work with you on creating.
  • Group count: A number that tells you the number of possible buckets a user could be grouped in. Common values are: 3, 10, or 20

The structure of the value in the user profile is a single integer

  • Score: The prediction generated by Black Crow in the form of an integer, which can be as low as 1 and as high as the group count.

Group Count - Black Crow distributes scores on a page view basis. This means that:

  • Group count of 3 = 33% of page views in each score
  • Group count of 10 = 10% of page views in each score
  • Group count of 20 = 5% of page views in each score

Comparison Group - a collection of page views the current page view that is scored is compared against.

  • site = group means the score is relative to all page views across the whole website
  • page = group means the score is relative to all page views that happened on this same  URL path

Score

  • A score is an integer representation of the raw prediction of your propensity model benchmarked against a comparison group. A higher score represents that this user is more likely to complete the action your model is predicting compared to other page views in the given comparison group.

Examples:

  • A score of 10 with a group count of 10, and a comparison group of site means this page view is in the top 10% likelihood of all page views to complete a purchase.
  • A score of 2 with a group count of 3, and a comparison group of page and a URL path equal to “/cart” means this page view is in the middle 33% likelihood of all cart page views to complete a purchase.

Let’s simplify & automate your marketing campaigns

Contact Us