Conversion modeling to track user data in an era with no third-party cookies

For years, multi-touch attribution tools and third-party cookies have been the go-to solution for tracking customers’ paths to conversion. However, as we wave goodbye to third-party cookies, understanding your customers’ complete conversion journey will become increasingly challenging.

With the decline of third-party cookies, advertisers face a challenge in tracking user pathways on their websites. This loss of tracking capability means brands can no longer directly connect users’ ad interactions to conversions, whether those people are repeat visitors or come from paid or organic traffic sources.

This gap in measurement calls for new solutions, such as conversion modeling, to help marketers adapt and regain insight into their customers’ behavior.

In short, conversion modeling is a framework to analyze the effectiveness of marketing campaigns.

This approach replaces outdated multi-touch attribution models that are no longer suitable for today’s complex customer journeys and cookie-tracking limitations. Instead, using machine learning, companies can evaluate the incremental impact of each visit based on website visitor behavior data, even if a final conversion can not be observed. Thus empowering advertisers to optimize campaigns for desired outcomes such as increased sales, registrations, or subscriptions.

Multiple tools on the market offer conversion modeling but the most popular are Google Analytics 4 and Google Ads which use conversion modeling to predict unobserved conversions without identifying individuals.

Conversion modeling offers several advantages for companies aiming to optimize their marketing strategies and better understand their customer’s behavior:

• Identify barriers and improve your conversion rate: Understand conversion paths across devices and channels resulting from ad interactions while also spotting roadblocks to conversion.
• Improve automatic bidding: Fill data gaps caused by privacy regulations, ensuring automated bidding decisions rely on accurate information about website or app activity rather than assumptions.
• Improve your marketing ROI: Make data-driven decisions and ensure efficient spending of your marketing budget by targeting customers more likely to convert. Leading to better results and higher conversion rates.
• Accurate yet privacy-focused measurement: Obtain actionable data while safeguarding your user identities and remaining compliant with global privacy laws.
• Gives you a competitive advantage: Many companies will struggle once third-party cookies disappear. By implementing conversion modeling now, you proactively set yourself up for success.

Conversion modeling uses machine learning to assign links between ad interactions and conversions accounting for cases where cookies and identifiers weren’t available.

To do this, ad interactions are separated into two groups: one group has a clear, observable link to conversion, while the other contains those without such a clear link.

Conversions with a clear path are further divided into subgroups to identify more specific patterns. For example, the rate of product purchases on weekends may differ from weekdays. And it may differ on weekday mornings versus afternoon versus evening time.

Then, machine learning predicts characteristics for the unidentified ad conversions based on known data and characteristics from clear conversion paths. Oftentimes, modeled conversions are only included in your reporting when there is a high level of confidence that an ad resulted in a conversion, ensuring accurate reporting and optimization.

Google is ending third-party cookies for all Chrome users in 2024. However, in order to help marketers and advertisers continue to reach the right audience, Google offers conversion modeling to help optimize campaigns more effectively.

Using known customer and conversion data, Google Ads will predict conversion accurately. It uses machine learning to maintain accuracy in conversion models across a diverse set of ad interactions and conversion actions.

Furthermore, Google Ads offers an enhanced conversion modeling tool that helps advertisers track their online advertising success more accurately by connecting user actions on their website with Google Ads campaigns. This is crucial for the future as it moves away from relying on cookies for tracking and instead matches up user data like email addresses in a privacy-conscious way.

By using hashed data and matching it with signed-in Google accounts, advertisers can measure the impact of their ads more effectively without compromising user privacy.

Imagine you’re running an online store that advertises across various platforms such as desktop, tablets, and smartphones. When customers interact with your ads on different devices, it can be challenging to link those interactions together due to the lack of available cookies.

Without modeled conversion techniques, you might miss attributing some conversions to the customers who interacted with your ads. This gap in attribution creates a problem because you won’t have a complete picture of how customers journeyed to conversion.

However, by implementing modeling techniques, you can fill in these gaps. Tools like Google Ads Conversion Modeling will analyze observable data and historical trends and can confidently connect ad interactions with conversions. Providing you with a clearer understanding of your customers’ paths to conversion.

To remain compliant with global data privacy laws, pairing conversion modeling with Google Consent Mode is vital.

Google Consent Mode is a tool that enables websites to communicate users’ cookie consent choices to various Google tags that help measure website and advertising performance. So when a user has not consented to personalized ads, Google Consent Mode enables marketers to still understand a person’s behavior.

Google Ads conversion modeling, on its own, may not be fully privacy compliant as it relies on tracking user interactions and conversions through cookies. However, when combined with Google’s Consent Mode, advertisers can respect users’ consent choices for personalized ads and analytics cookies while still effectively measuring conversions.

It adjusts how site tags behave based on a person’s consent status. This means that tags are blocked until your website visitors interact with a consent banner. No data is sent to Google before user interaction. And if consent is denied, no data is transferred at all. Thus helping you bridge the gap in campaign performance when cookie consent is not granted.

If you use Google Analytics 4 (GA4) for modeled conversions, you need to be careful of how you collect and use personal data. Because you may not be fully GDPR-compliant when it comes to cookies.

The solution is to pair GA4 with Google Consent Mode to manage user consent effectively and ensure compliance with privacy regulations like GDPR. Doing so allows you to align your data collection practices with user consent choices. Thus enabling your company to gather behavioral data without infringing on people’s privacy.

Google Tag Manager (GTM) simplifies tag management by allowing businesses to deploy and edit tags without the need to edit code directly. However, the tags and pixels added to GTM by the website owner may collect site visitors’ personal data and may not be compliant with GDPR if not properly managed.

That’s why pairing Google Tag Manager with Google Consent Mode is crucial for managing user consent effectively and ensuring compliance with privacy regulations. When Google Consent Mode is implemented, Google tags adjust their behavior based on user consent choices.

Conversion modeling presents a few challenges for marketers and advertisers.

The first is gathering enough accurate data since customers often show their preferences through actions rather than explicit statements. This also makes defining customer behavior difficult. To overcome this, marketers can implement tactics like website tracking and customer surveys, to better understand customer behavior and build accurate models.

In addition, as identifying conversion rates from different channels becomes more difficult, setting an ideal conversion rate is tough. The solution begins with investing time in comprehending your customer preferences and behaviors to accurately define conversions and relevant preferences or behaviors. Pair information with customer knowledge from your CRM with customer surveys to gather accurate information about where your customers come from and found out about your company. Then use this knowledge to set realistic conversion rates for different channels.

Successful conversion modeling is essential for optimizing marketing strategies and improving conversion rates. Here are some best practices to implement for effective conversion modeling:

• Define clear objectives: Clearly define the objectives you want to achieve through conversion modeling, whether it’s optimizing marketing campaigns, improving customer retention, or increasing sales.
• Gain a deep understanding of your customer behavior: Develop an understanding of customer behavior to build accurate conversion models. This is crucial for defining conversions accurately and tailoring strategies to meet customer needs.
• Take a data-driven approach: Utilize data-driven insights to better understand customer behavior, preferences, and interactions. Data collection methods such as CRM integration and customer surveys can provide valuable information for building accurate models.
• Be patient: Implementing a successful conversion model takes time and patience. Be prepared to be flexible as you work through the process, making adjustments based on insights and data analysis.
• Regularly monitor and twerk your efforts: Regularly review key metrics, conversion rates, and user behavior data to identify areas of improvement and optimizing.

A Google-certified consent management platform (CMP) is instrumental in enhancing both conversion rates and modeled conversions by ensuring compliance with data privacy regulations and fostering trust with customers.

CMPs like Usercentrics or Cookiebot™ empower businesses to achieve regulatory compliance, build user trust, and obtain valid audit-proof consent for the use of cookies and web technologies on websites and apps. This transparency not only helps capture valuable marketing data but also secures increased ad revenue, ultimately optimizing marketing strategies effectively.

Successful online measurement relies heavily on cookies that log useful information about what happens after a person has clicked an ad. Information such as location, user device, browsing history, website interaction, and more.

However, due to privacy concerns and legislation such as the General Data Protection Regulation (GDPR), the ePrivacy Directive, and the California Privacy Rights Act (CPRA), there are more and more scenarios where it’s not possible to observe whether a conversion has taken place.

So in a cookieless world, conversion modeling helps fill gaps in the customer journey. It enables marketers to better understand their customers’ paths to conversion even when direct measurement is not possible.

As people become more aware and concerned about their personal data online, and global regulations cater to this fear, conversion modeling will grow in importance. The rise of modeled conversions enables brands to make data-driven decisions about where and how to invest in advertising, even as the industry shifts away from third-party cookies.

Modeled conversions help brands connect better with consumers. They give insights into conversions from ads shown to people who aren’t specifically targeted. This helps create more relevant campaigns, making messages resonate with more people.