How does DDA Work?

Data-driven attribution (DDA) works by using machine learning algorithms to analyze conversion data and determine how much credit to assign to each touchpoint in the customer journey.

Overview on how DDA works

1. Data collection: DDA collects data on all touchpoints in the customer journey, including ad impressions, clicks, website visits, and conversions across different channels and devices.

   
   

2. Machine learning analysis: The algorithm analyzes both converting and non-converting paths to understand how different touchpoints impact conversion probability.

   
   

3. Factor consideration: DDA incorporates various factors in its analysis, such as:

   • Time from conversion

   • Device type

   • Number of ad interactions

   • Order of ad exposures

   • Type of creative assets

   
   

4. Counterfactual approach: The model compares what actually happened (conversions) with what could have occurred to determine which touchpoints are most likely to drive conversions.

   
   

5. Credit assignment: Based on this analysis, DDA assigns fractional credit to each touchpoint according to its estimated contribution to the conversion.

   
   

6. Continuous learning: The model continuously updates and refines its attribution based on new data, adapting to changes in customer behavior and marketing strategies.

   
   

7. Customization: Each DDA model is specific to the advertiser and conversion type, taking into account the unique characteristics of the business and its customers.