This new approach enhances multiple assignment attribution, giving marketers full transparency into how credit is distributed across their marketing channels.
Why did we choose this Approach Over Google’s DDA?
At Mapp, we believe transparency is key, and we’ve chosen the latter as the foundation for our new attribution feature. In multiple assignment attribution, businesses often face a choice: trust Google’s Data-Driven Attribution (DDA), a machine-learning-driven approach, or implement a transparent, rule-based model like Simplified Shapley with Positioning.
Google’s DDA works well for fully automated, large-scale campaigns within Google’s ad platform. However, for businesses looking for trust, transparency, and flexibility, our new feature offers a superior alternative. It ensures that every marketing touchpoint is fairly credited while maintaining computational efficiency, giving businesses the insights they need to make better marketing decisions.
What’s the Difference?
Google’s DDA is a black-box system that automatically assigns credit to marketing touchpoints based on historical data. While useful for large-scale advertisers operating solely in the Google ecosystem, it lacks transparency and requires significant data volume to be effective.
Our Simplified Shapley with Positioning method is built on cooperative game theory, ensuring that every marketing touchpoint receives due credit based on its actual contribution to the conversion journey. Unlike Google’s model, it explicitly incorporates positioning effects, acknowledging that a touchpoint at the start of a journey plays a different role than one right before conversion. This is what it looks like:
.png)
Why Transparency Matters
One of the biggest limitations of Google’s DDA is that it functions as a black box. This means you can’t always understand why credit is distributed as it is.
Our model, as you can see in the example above, offers complete transparency. Every attribution decision is based on clearly defined rules, allowing businesses to trust their data and make informed budget decisions without relying on proprietary algorithms.
Computational Efficiency Without Complexity
Traditional Shapley methods can be computationally expensive, but our simplified approach dramatically reduces overhead. Instead of calculating attributions across all possible channel combinations, our model uses an optimized closed-form formula, making it scalable and practical for businesses of all sizes.
This approach is described in detail in the paper Shapley Value Methods for Attribution Modeling in Online Advertising by Kaifeng Zhao et al. (2018).
Who Benefits Most from Our Approach?
Businesses using Mapp Cloud for multi-channel attribution.
Marketers who value transparency and want to understand how credit is assigned.
Organizations that prefer rule-based models rather than machine-learning-driven black boxes.
Companies looking for flexibility in how attribution is structured and applied.
With this latest addition, Mapp Cloud is empowering marketers with a clear, fair, and effective way to optimize their marketing spend. Try it today and gain full control over your attribution modeling!