The Total Impact Attribution Model is a cutting-edge marketing attribution tool that leverages First-Party Pixel Data and Post-Purchase Survey Data, powered by Machine Learning and Artificial Intelligence. This model is designed to provide a comprehensive understanding of which marketing channels are driving the most revenue, offering a sophisticated alternative to traditional view-through attribution methods. Unlike view-through attribution, which relies on views and impressions, the Total Impact model focuses on click-based data to highlight the most revenue-generating channels.

The development of the Total Impact model was driven by significant changes in the digital marketing landscape, such as the data loss caused by iOS14 and the phase-out of Google Analytics’ Universal Analytics. These changes underscored the importance of collecting first-party data and consolidating store metrics in a single platform.

Building on the foundation of Triple Whale's previous attribution models, the introduction of Total Impact incorporates Artificial Intelligence to help businesses navigate these challenges.

Incorporating machine learning into advertising data provides a competitive edge by identifying patterns and predicting customer behavior, which leads to more targeted campaigns and improved customer engagement. This enhanced capability is crucial as it offers a comprehensive analysis of advertising channels.

While Triple Whale has previously helped analyze the potential of advertising channels using Triple Attribution, the Total Impact model goes further by utilizing various data points to measure the impact of prospecting ads accurately. This deeper insight is essential as it clarifies advertising investments and helps understand which tactics are winning or losing, thus informing future marketing tests.

The Total Impact model works by integrating first-party data, zero-party data, and machine learning, based on a weighted model that aims to attribute revenue according to which channels provide the most impact on the purchase decision. For instance, if a click on Facebook aligns with a survey response indicating Facebook, the model gives more credit to Facebook. This model examines the customer journey from the initial touchpoint to purchase and beyond, using click-based attribution to distribute credit. It considers a wide range of factors, including survey data, ad impressions, clicks, website visits, and email opens, to determine the most impactful touchpoints.

As new data becomes available, the model continuously learns and adapts, providing increasingly accurate insights over time. This capability helps businesses stay ahead of the curve and make data-driven decisions.

By redistributing 100% of Shopify sales using click data, survey data, and proprietary modeling, the Total Impact model credits the most impactful channels and campaigns.

While it allows for the review of Triple Attribution metrics against Total Impact metrics down to the ad level, users cannot click on specific orders or journeys (as revenue can be split among channels). However, this comprehensive approach provides clarity on advertising investments and enhances understanding of which marketing tactics are successful.

To utilize the Total Impact model, businesses can visualize the weighted success of their marketing sources, channels, campaigns, ad sets, and ads. The model distributes store revenue based on the impact on purchase decisions, ensuring statistical significance and accuracy through bias correction.

This model requires the use of either the Triple Whale Post-Purchase Survey or an integrated post-purchase survey from KnoCommerce or Fairing. Bias correction, based on survey data using AI, mitigates the effect of random survey answers, ensuring the model's accuracy.

If your Pixel table shows a message requesting you to connect or install a post-purchase survey (such as the one in the screenshot above), there are several steps you can take. First, consider installing Triple Whale's free post-purchase survey tool, which can be set up quickly to start collecting data.

Alternatively, if you are already using one of our partner post-purchase survey tools, such as Fairing or Kno, you can easily connect it to Triple Whale. It's important to note that Triple Whale requires at least seven days of post-purchase survey data to effectively power the Total Impact model, so timely installation and data collection are crucial.

Creating a Media Mix Model (MMM) typically requires significant time and financial resources, often necessitating millions of dollars in spending and at least two months to gather sufficient data for accurate results. In contrast, the Total Impact model offers a practical solution that has been tested against MMM, showing similar results without the extensive data and time requirements. This efficiency makes it an attractive option for businesses seeking to credit successful campaigns accurately through click-based attribution.

Total Impact is similar to MMM in that it uses aggregate data to determine which channels and campaigns are most impactful over time. It is recommended to review the model with the last seven days selected to avoid skewing results from recent activities. For day-to-day optimization, businesses should use Triple Attribution or Last Click models with 1-day-click windows applied.

While the Total Impact model is highly effective for long-term analysis, it is not suitable for immediate impact analysis. If businesses need to understand the impact of a new ad, campaign, or marketing channel on the same day, they should use Triple Attribution instead. Total Impact is best viewed based on a seven-day average to provide accurate insights and inform data-driven decisions.

If you encounter a message (such as the one above) indicating insufficient data while selecting the Total Impact model, it means your store lacks enough post-purchase survey data to generate a statistically significant output. This can occur when the volume of survey responses is too low to provide reliable insights.

To address this issue, you should verify that your survey is present on your post-purchase page (commonly found at the "/thank-you" page in your checkout flow). Additionally, check if any third-party apps, such as upsell offers, are positioned above your survey, as this can lead to lower response rates. Ensure that your submit button is visible and easy to see, aiming for a response rate of 30% or higher to gather sufficient data.