Custom Attribution Models: A Tailored Approach to Attribution

In the rapidly evolving world of marketing analytics, accurately measuring the impact of various marketing touchpoints on customer conversions is essential for driving success. Traditional attribution models have long served as valuable tools for understanding the customer journey, but they often need to capture the unique dynamics of individual businesses.

This is where Custom Attribution Models step in, offering a more sophisticated and personalized approach to credit allocation. By tailoring the attribution process to align with a business's specific needs, goals, and target audience, custom models provide marketers, analysts, and CMOs with deeper insights and data-driven decision-making capabilities like never before.

Note: This article was originally created in 2017, and since then it has been updated multiple times with the new trends in marketing attribution modeling and machine learning in marketing.

• Flexibility and Personalization: Custom attribution models are highly flexible, enabling businesses to define their rules for attributing credit. Marketing specialists and analysts can create bespoke models that align precisely with their business goals, marketing strategies, and customer behavior.

• Tailored Data Collection: A robust data collection process is essential to implement a custom attribution model successfully. Businesses must gather data from various sources, such as website analytics, CRM systems, social media platforms, email interactions, and offline touchpoints. This granular data allows a more accurate assessment of each touchpoint's conversion contribution.

• Weighted Attribution: Custom models often use weighted attribution, where different touchpoints are assigned varying degrees of credit based on their significance in influencing the customer journey. This approach acknowledges that specific touchpoints may substantially impact conversion more than others.

• Integration of Online and Offline Interactions: With the rise of omnichannel marketing, customers now interact with brands across multiple online and offline channels. Custom attribution models can seamlessly integrate data from both worlds, offering a unified view of the customer journey.

• Iterative Approach: Developing a custom attribution model is often an iterative process. Businesses may need to experiment with different methodologies, test results against actual performance, and refine the model over time to ensure its accuracy and effectiveness.

Custom attribution models offer several key advantages over traditional, one-size-fits-all approaches. By tailoring the attribution process to the unique characteristics of a business, marketers, and analysts can gain deeper insights and make more informed decisions.

Custom attribution models provide a comprehensive view of the customer journey, allowing businesses to understand the impact of each marketing touchpoint on conversions. Considering multiple touchpoints and interactions, these models accurately represent how customers engage with the brand. This level of insight empowers marketing specialists and analysts to identify the most influential channels and optimize their strategies accordingly.

With granular insights into the effectiveness of different marketing touchpoints, custom attribution models enable data-driven decision-making. Marketers can allocate their budget and resources more efficiently, focusing on the channels and campaigns that drive the best results.

One of the significant advantages of custom attribution models is their adaptability to changing business needs and strategies. As marketing objectives evolve, businesses can modify their custom models to reflect new goals and align with marketing campaigns.

In today's omnichannel world, customers interact with brands across various online and offline touchpoints. Custom attribution models can seamlessly integrate data from both realms, offering a unified view of the customer journey. This integration helps businesses understand how online and offline interactions influence conversions, leading to more informed marketing decisions.

Custom attribution models provide a more accurate assessment of marketing campaign performance. CMOs can gain deeper insights into which campaigns and channels drive the most significant results, allowing them to make strategic decisions to optimize marketing efforts and maximize return on investment.

Custom attribution models can be tailored to specific industries, products, or customer segments. This level of customization ensures that the attribution approach aligns with the unique characteristics of niche markets, providing more relevant and meaningful insights for businesses targeting specific audiences.

The challenge for analysts is to bring together all the data sources needed for the calculations.

Here’s the good news: if transaction data is already sent to Google Analytics 4 and advertising campaigns have all the necessary UTM tags, establishing the settings will only take about half an hour. You won’t even have to seek assistance from developers.

Just use OWOX BI and Google Tag Manager. More details about custom tags in Google Tag Manager can be found in this blogpost.

More about combining data can be found here.

After combining the data, an analyst should set up the attribution model. Marketers can also create new attribution models or change existing ones, but it would be better if an analyst created the first model. This will ensure the data from the connected sources is accurate. If the probability of progression to the next step is more than 90% or less than 5%, there’s something wrong.

The result of an analyst’s work is all the data brought together to enable calculations in Google BigQuery, and at least one calculated attribution model.

Marketers' challenge is evaluating advertising campaigns and drawing conclusions about how to reallocate the advertising budget most efficiently.

The good news for marketers is that to see the real value of advertising campaigns; they need only start typing their questions in the OWOX BI Smart Data.

...and see what campaigns were undervalued, or overvalued, in the Last Non-Direct Click attribution model:

This is a valuable report. It demonstrates how campaigns could be re-evaluated if you considered their contribution to the progression through each stage of the funnel, not only to the last. A marketer can easily manage the results by adding and editing stages within the funnel, combining data from multiple devices, or ignoring free traffic sources in the attribution model.

For example, if the user sessions on multiple devices are combined using UserID in the attribution model, the average length of a conversion path will increase. This happens because a customer can use multiple devices on their journey to a purchase. The credit designated for advertising campaigns will be allocated correspondingly to their channels

How do you apply the results of the attribution? This might be a genuinely challenging question for many marketing specialists. True, there’s no such option as considering the contribution of campaigns in Bing Ads in Google Ads. Much like advertising agencies, they're unlikely to share notes if you work with a few simultaneously.

If a marketer does nothing with that, the marketing channels will compete against each other to drive conversions. The success of one campaign will always mean that the other has failed. As a result, you’ll only be able to predict one thing about your advertising budget: there won’t be enough money.

You won’t be able to answer such questions as "Why does CPA increase for one channel when I exclude the other one?" or "How do I increase sales without seeing ROAS drop?".

Marketing experts should set individual goals for each to ensure that your advertising campaigns work as a team towards a common goal. The goals should be set with their strengths and mutual impact in mind. Display campaigns shouldn’t be evaluated only in terms of the transactions, and Email channels shouldn’t be considered just in terms of the number of attracted customers.

The easiest and quickest way to do so is to adjust the target CPA for each campaign while considering the particular correction factor. This factor is calculated as a ratio between the revenue attributed to an advertising campaign in the Funnel-Based attribution model and the revenue attributed in the Last Non-Direct Click attribution model. An example of the correction factor is given in the last column in the table below.

Campaigns highlighted in green have a correction factor of greater than 1. These campaigns are undervalued in the Last Non-Direct Click attribution model. This happens when a campaign, more often than others, contributes to the progression on the upper stages of the customer journey but is followed by another campaign, which gets all the credit for the conversion.

The campaigns highlighted in red have a correction factor of less than 1; these campaigns are overvalued. For example, the Last Non-Direct Click attribution model could assign all credit for the conversion to the Email channel. Meanwhile, campaigns that attracted visitors to a website where they submitted their email addresses garnered no credit.

With OWOX BI Smart Data, a marketer can determine the efficiency of each advertising campaign and reallocate the advertising budget accordingly.

For example, reallocate the budget towards undervalued campaigns, and reduce the budget for overvalued ones. More details about the shortcomings and advantages of different attribution models can be found in our blogpost.

As a result, by applying the attribution model, which evaluates each touchpoint in the conversion process, marketing specialists can achieve an up to 25% increase in revenue in the project at the same level of advertising budget:

It’s important to understand that some campaigns' costs per conversion will increase. However, the cost per conversion will decrease for the project as a whole due to this well-coordinated teamwork.

Marketing experts can always check the accuracy and efficiency of attribution models.

What’s the challenge for CMOs, if the data’s already brought together by analysts and advertising campaigns are managed by marketing specialists? A chief marketing officer plays a principal role in inspiring their team, from being Last-Click apprentices to becoming real attribution masters. In the following stages, a CMO motivates their team by tapping into their strengths and resources while controlling the accuracy of the calculations.

How can you ensure that the ROAS you’ve got provides an accurate evaluation of the performance of your advertising campaigns?

Run a test for two user segments (e.g.) and compare results. In segment A, use your old attribution model. In segment B, apply the funnel-based attribution model. Success would appear in the chart below:

As a result, your business will be rewarded with transparent analytics and a more effective way to achieve your sales targets.

In the future, custom attribution models will see a surge in integrating cutting-edge technologies such as AI and ML to provide real-time, cross-device, and cross-platform attribution insights. These models will prioritize privacy compliance while incorporating contextual factors and predictive capabilities.

Custom attribution will become more niche-specific, catering to diverse industries and customer segments.

Additionally, transparency in the attribution process will be emphasized, allowing marketers to make more informed decisions and optimize their strategies for better results. Custom attribution models will continue to evolve, offering marketers innovative tools to gain deeper insights and achieve marketing enlightenment in an ever-changing digital landscape.