When talking about marketing and personalization, we all know it is table stakes to know your clients very well. After all, if you don't know them, how will you serve them the best way possible?
Let's say you work for a financial service company. How will you know what services the customer is interested in? Is it worth focusing on publicizing investment products if they are interested in a no yearly fee credit card?
Although thousands of platforms promise to help brands understand their clients (what they buy, how often they access the website, what their interests are, etc.), the technical data world can be pretty imprecise at an individual level. There is plenty of fake information on individual customers.
Understanding each customer as a unique person is essential so that brands know exactly which users their media campaigns lead to the site. That is impossible if you can't recognize the same person interacting with various devices.
Stop for a minute and ask yourself: how many devices do you or your family use every day? In 2021, a research study by Deloitte collected data stating that the average U.S. household has 25 connected devices – more than double the 11 that the average household had in 2019.
As digital campaigns proliferate on countless devices and channels, the challenge of the marketing professional becomes increasingly more outstanding. Understanding the characteristics of those who use only one device is no longer a competitive advantage: now, we need to understand the person who interacts with at least two devices.
Identity resolution is the solution for recognizing your customers. This awareness enables us to design a coherent image of people as they navigate among channels and devices and integrate through different identifiers. It can include, for example, emails, phone numbers, cookies, and device IDs.
The way your technology partners approach identity resolution makes a significant impact on all your marketing decisions. For that reason, we need to understand the concepts linked to it very well.
An individual's identity includes offline identifiers, such as name, address, phone numbers, and online ones, such as email addresses, cookies, ad IDs, etc. Identity resolution may look complex, but the failure to understand how it works can result in decision-making based on false information.
An isolated identifier is not enough to identify a person in most cases. For example, let's look at two identifiers: address and name. The address may not be enough when used alone as it can relate to more than one person. However, when linked to a name, there are increased chances of recognizing a person.
Identity resolution makes it possible to connect the dots between these identifiers more precisely. This is scalable and compatible with specific privacy policies for producing a stable and consistent view of your customer. Knowing what the right questions are on the approach a technological partner uses for identity resolution is essential to be confident that your methods will increase your ROI.
Next, we’ll discuss how identity resolution works and the different approaches in the market.
There are two approaches to identity resolution: deterministic and probabilistic. These terms tend to imply value judgments, yet no characterization is precise.
For example, deterministic data can be an email address related to a cookie or an ad ID. On the contrary, you can use probabilistic data for making inferences based on all the behavioral signs and interactions of customers.
The deterministic approach evaluates an explicit link among identifiers, while the probabilistic method shows how implicitly strong that connection is. It is essential to assess three factors when using identity resolution:
- Precision: it is critical to use only precise links to guarantee that the resolution always connects identifiers truly from the same person
- Wealth: focus on the complexity of understanding the customers' profiles, addressing digital and offline channels, devices, demographic data, etc
- Scale: look at the amount of data and the possibility of capturing more links on the customer and create the largest possible target public.
The deterministic and probabilistic methods both have their advantages and disadvantages when seeking these objectives for actual overall identity resolution.
The deterministic method helps create a single customer profile from two directly linked identifiers. That is possible, for example, when a user logs in to a site using an email address on a computer and later purchases from the same website from their smartphone. Then, the two identities (one from the computer and the other from the smartphone) will be linked through email, and the profile will contain information from both devices.
Although the deterministic approach is genuinely omnichannel, it connects identifiers from the digital and offline worlds. It can be problematic as it is common to share accounts among relatives and friends for specific subjects. When you share your Netflix password, or a friend uses your computer to check their email, you can have incorrect links. Besides that, due to its nature, deterministic data are limited in quantity (as there is a small and finite number of explicit connections), interfering with the model's scalability.
On the other hand, the probabilistic approach analyzes several signs for discovering which identifiers can be highly dependably linked. For example, suppose the same ID from a desktop ad and cookie visit a site from a residential IP address several nights per week. In that case, the probabilistic methods define that all these signs belong to the same family.
Additionally, suppose two devices share the same data frequently (a computer and a smartphone, for example). In that case, both are connected simultaneously to various IP addresses, such as at home, at work, or at an airport, so we can assume that the devices belong to the same person.
The probabilistic approach is handy for doing away with false information. It analyzes a large variety of data instead of just binary correspondences, as in the deterministic method. Whereas online data is limited, it is ineffective when speaking about identity resolution involving interactions in the real world.
Some technologies use deterministic and probabilistic methods to create a precise and scalable approach. Theoretically, this seems like the best of both worlds. Unfortunately, it is slightly different when put into practice due to low-quality data, imprecise links, and contaminated data clusters.
For the hybrid method to succeed, marketing professionals need to apply deterministic approach results as a source for probabilistic approaches to evaluate which connections are relevant. In other words, you can't just match deterministic data with probabilistic data after creating both by separate methods. It would be like adding yeast to a piece of baked bread and waiting for it to continue rising.
Identity data has become vitalized in the acquisition and increasing customer loyalty.
It means you can segment an individual or family precisely within the marker and decide to connect contact point data with purchasing data or other results. You need a stable identity resolution system to do this correctly, from point to point, able to evaluate and make decisions on an individual level, tracking each contact point granularly.
The importance of a robust identity resolution for any brand that intends to be more focused on the customer hasn't been questionable for a long time. Marketing professionals must become the most demanding regarding identity and get an in-depth understanding of the methodologies used by their technological partners. It is essential to understand data science behind keywords, going beyond what the word "deterministic" suggests and the risk "probabilistic" implies.
You need an in-depth understanding of identity resolution that will allow you to confirm if the marketing platform and measurement approach can operate at the highest levels of granular, consistent, and stable identity. If you cannot provide the best online and offline experience in various channels to the right consumer, your results will probably be unsatisfactory, no matter how good your ideas, campaigns, messages, or algorithms are.
Having identity resolution as one of our features, we help you understand your users in-depth through their interaction in different channels. We believe this is the best way to create a unique and personalized experience for each one of them.
We use the hybrid method the right way so you can get the best out of your data, regardless of how many devices each user accesses or how many different domains your company has.
In addition, we only use data informed by users, which guarantees privacy and security at all times of the user journey. If you want to better understand how our engine works or how we can help you create better browsing experiences, please get in touch with us! We will be happy to chat with you :)