Case Study
Identity Health Score
Helping users understand and mitigate the risk of identity theft on the Dark Web
Using machine learning to help users understand how their actions can safeguard their identities.
Experian's B2B2C business unit, Experian Partner Solutions, offers financial wellness and identity protection solutions to our partners' users through white-label platform portals, APIs, or custom solutions. Experian's innovative identity protection solution, CyberAgent, is known for its ability to notify users about any personally identifiable information found on the Dark Web, helping to reduce the risk of identity theft. The Dark Web, often misunderstood, poses a significant threat to identity security, and CyberAgent effectively addresses this challenge.
Experian and its predecessor, CSID, have long aimed to develop a personalized score to help users understand the risks their identities face from the Dark Web. This score would be similar to a credit score for one's identity.
After several unsuccessful attempts, Experian’s data scientists developed the Identity Health Score using advanced machine-learning techniques and data from CyberAgent, FraudNet, and PreciseID. Our goal was to use the algorithm and score to provide users with a better understanding of their identity risk level and how to manage it.
Our post-launch analytics show that subscribers who diligently followed their Identity Health Score action plan experienced a significant 12% reduction in fraud events.
Our task was to leverage the power of the new algorithm and score—a significant innovation for us—to empower users with a deeper understanding of their cyber risk levels. This understanding will enable them to take proactive steps to reduce their risk over time.
Identity Protection
May 2023 Beta
Nov 2023 GA
Product Design Lead
Stakeholders
Data Scientists
Product Owner
Product Designer Researcher
Tech Product Manager
Developers
Before I engaged with the project, stakeholders and the lead UX researcher conducted two rounds of user interviews. The key insights from the interviews were that CyberAgent users don’t always understand:
I conducted an in-depth competitive analysis to see how others solved the problems our research uncovered and how we could improve upon it in our solution. A few things I noticed in the evaluation are:
The level of risk associated with receiving an alert;
What to do about the alert itself, and;
How to proactively protect their identity and prevent alerts.
To better understand our users’ goals and experiences, I created user journeys based on our existing proto-personas. These were very useful in helping me plot the user flow, add context where needed, and improve comprehension. They were also very helpful in supporting the product's expansion into more than just a simple numerical score.
My two key takeaways from this exercise were:
I quickly realized that the algorithm alone was not sufficient to capture all the information we needed to generate an accurate and meaningful score. For instance, if we discovered a user's credit card number but they had already replaced it, their score would be higher than if they had not.
To address this, I created a survey to collect data on user habits beyond our Dark Web data. We decided that users would need to complete the survey before they could view their initial score. Additionally, the survey proved to be beneficial in demonstrating the level of personalization to users and enhancing their understanding of the score.
Users wanted to know more about what went into the score to better understand it and its value, but they would not read large blocks of text. The content needed to be succinct and discreet but easy to find.
The survey proved very useful beyond its original purpose of increasing score accuracy. The questions gave the users their first glimpse of the data used. I also included:
Initially, IHS was only a score, but we quickly realized that once users understood their score, they wanted to know how to improve it.
I designed a protection plan listing actions the user could take and mark as "done," along with content explaining what information we uncovered and the risk posed by exposing it. The actions were the questions from the initial survey that the user answered negatively. This amount of content would be a significant lift for an organization without a dedicated writer. Fortunately, I realized we could leverage existing alert content for most of it. Then, I wrote ten more for items unrelated to Dark Web data.
Initially, IHS was only a score, but we quickly realized that once users understood their score, they wanted to know how to increase it.
I designed a protection plan listing actions the user could take and mark as “done,” along with content explaining what information we uncovered and the risks posed by exposing it. The actions were the questions from the initial survey that the user answered negatively. This amount of content would be a big lift for an organization without a dedicated writer. Fortunately, I realized we could leverage existing alert content for most of it. Then, I wrote ten more items unrelated to Dark Web data.
Initially planned to be a simple score, this product evolved into a robust identity protection tool and an ongoing engagement driver with optional paths for upselling. Partners that offered our privacy tools (VPN and Password Manager) could enable CTAs within relevant recommended actions.
With 62 alert types and ten recommended actions, this product had high content needs but no on-staff writer. Fortunately, I realized that portions of our existing alert content could be edited and reused.
Good concept. Trustworthy. Like the action items in the ID protection plan. Score gives me an insight on what can and cannot be done.
Love it. Simple and not time-consuming. You can keep track of your security.
Simple, nice and compact, easy to read in one page. Does not feel super busy. Like how it's a checklist. You start doing things and check it done, it fluctuates and lets you know (plan and score get updated). Someone with a low score would need to be proactive.
I like that I can do things actively on my end to improve my score. Want to keep it in the healthy green range. Will enjoy marking something done and watching the score go up. I will set it up by adding all my details to be monitored.
Back to homepage