Attribution best practices

Picking the right attribution model for your organization depends on a number of considerations. This article explores a methodology and some general best practices:

Exploratory Analysis

This phase consists initially of understanding customer behavior and defining conversion metrics. Based on the conversion metrics, tools like Data Feeds (for raw data) or Analysis Workspace facilitate your understanding of

For example, if 50% of customers touch 3 channels before converting, is there any interaction among those 3 channels?
To expand your understanding, perform upper- and lower-funnel analysis.

Upper-funnel analysis

Upper-funnel analysis channels are used to create brand or product awareness. For example, the goal of most TV ads is brand awareness. Use the Time decay attribution model since people will forget about your TV ad over time.

Lower-funnel analysis

In lower-funnel analysis, the assumption is that people already know about your brand and you want them to convert. Use email, push notifications, or Facebook ads.

Rule-based attribution

The purpose of this step is to validate your hypotheses.

Example 1

Suppose that your hypothesis is: “My first-touch channel has more impact on conversion than my last-touch channel.”

In this case, use the Inverse J-shaped attribution model to test this hypothesis. This model gives 60% of the credit to the first touch point.

Example 2

Suppose your hypothesis is: “In the travel industry, the attribution window is 60 or 90 days, not 30, because customers research a lot before buying.”

In this case, change your lookback window to 90 days.

Use algorithmic attribution

If you don’t yet have an attribution model that provides satisfactory answers to all of your questions, you can use algorithmic attribution. Because it is very hard to validate a large number of possible hypotheses and combinations, algorithmic attribution uses built-in algorithms to allocate credit across dimension items.

Other considerations