* **The Product**\
  ClosedLoop is a healthcare platform that gives providers, payers, and value-based care organizations the ability to make accurate, explainable, and actionable predictions of individual-level health risks.

* **The Problem**\
  Machine learning models don't allow users to check if representative samples, such as race, are impacted by label bias.

* **The Goal**\
  Assess whether a machine learning model uses a representative sample, is impacted by label bias, or may result in the unfair distribution of resources. After reviewing each metric, you can indicate whether the model has been validated and whether it is biased or unbiased.

* **My Role**\
  Product designer from conception to delivery.

* **My Responsibilities**\
  User-journey mapping, paper and digital wireframing, low and high-fidelity prototyping, conducting usability studies, iterating on designs, and design QA.

### **Insights from User Testing**

\
User Understanding

Even though the platform has multiple tooltips to add less visual weight, users needed clear and helpful instructions on how to evaluate bias and fairness that needed to be displayed without tooltips.

```cv
gallery
{"layout":"hscroll","images":[{"src":"https://firebasestorage.googleapis.com/v0/b/maitake-project.appspot.com/o/pages%2FYqNZBUOCstP50Pd3LXVrWXs3XDG3%2FFY7aImtWH2k9xnoTDbGN%2Faebea084-1d35-4776-bf33-fc61e5853b4d.png?alt=media&token=5202229b-1996-4a24-9daa-90a164f5de98","id":"aebea084-1d35-4776-bf33-fc61e5853b4d","width":1445,"height":700,"filename":"bf-user-understanding.png","type":"image/png","caption":"","border":false}]}
```

ClosedLoop / Bias & Fairness

Product Designer / Dad / Husband

Foundations of User Experience (UX) Design

Build Wireframes and Low-Fidelity Prototypes

Start the UX Design Process: Empathize, Define, and Ideate

Google

Conduct UX Research and Test Early Concepts

Implement multiple features for machine learning healthcare models.

Bulk Feature Creation

Allow users to explore files and databases from other cloud environments such as Amazon S3 while in the ClosedLoop platform.

File Explorer

Assess whether a machine learning model uses a representative sample, is impacted by label bias, or may result in the unfair distribution of resources. After reviewing each metric, you can indicate whether the model has been validated and whether it is biased or unbiased.

Bias & Fairness

- Served as a volunteer representative that focused on the Latino population of greater Salt Lake City area
- Managed, trained and led 180 volunteers in the Salt Lake City Area
- Directed relations between volunteers and local church leaders
- Served as the assistant to the Mission President

Esteban Aravena

Projects

Volunteering

Certifications