Fraud Detect utilizes expert machine-learning technology for government programs in Healthcare, SNAP, and Unemployment. Fraud Detect identified $50 million in overpayments, which led to $18.7 million in recoveries by Medicaid Inspector General.
The existing application looked and behaved more like a website than a web application. There were numerous inconsistencies with the UI, from different font families and sizes being used, to colors that were not on brand, or colors that didn’t have the needed contrast to pass an accessibility review. There were also various user experience challenges, confusing UI elements, and the lack of a dashboard to provide users with actionable leads.
I traveled around the country to meet with clients. I sat with the users and watched how they used the application, and how they didn’t use the application. I developed user personas, and documented pain points, and areas of opportunity for the team to build for clients.
Throughout the design process, I got feedback from SMEs, BAs, developers, the executive team, and clients. I built prototypes that allowed us to test interactions, and get feedback from users. This resulted in an easy rollout to clients who felt part of the redesign process, and were excited to get a much needed update to the application.