The taxonomy team develops and maintains centralized taxonomies, supporting 60 countries and 28 languages. Their work is mission critical to facilitate matching between jobs, job seekers and employers.
Problem Space
Whenever Indeed wants to enter a new market, a market-specific taxonomy (occupation family hierarchy) is critical to surfacing matches between jobs and jobs seekers.

It typically takes a year to create top level (parent) categories for occupations.

The team developed a ML prediction model to accelerate the process.

Analysts had make-shift tools to check and refine the ML predictions, but they were clunky and inefficient.
Role & Contribution
I was brought in to help. I re-worked the tools and workflows that analysts used. As the sole designer, I lead and executed on all aspects of the UX process.
I was on temporary assignment for one quarter. There was immense pressure to deliver value in a short amount of time.
The team went from over a year to build a top level taxonomy to 3 months without a drop in quality.

This had huge impacts on the Indeed’s ability to deliver more relevant jobs to job seekers in new and emerging markets faster.
Foundational Context
Overall Analyst Workflow
Step 1: Hierarchy management (starting point)
Step 2: Category page (quick actions)
Step 3: Detail page (more attention needed)
Step 1: Hierarchy Management
The table was completely redesigned to help managers maintain a birds-eye view and analysts to better prioritize their work. Irrelevant fields were removed, clear status indicators and permission-based quick actions were added.
Step 2: Category Page
The revamped information architecture allowed analysts to quickly check, refine and take action on ML predictions. Even though the core experience didn't change much, these tweaks yielded gains in productivity.
Step 3: Detail Page
There were times when more attention was required to accurately classify a job into a certain category. The new focused experience allowed analysts to check references, compare and assign categories.
Creating a Vision
Leveraging insights from the MVP, I put together a 1 year vision on how the team could further improve the product.
Next Up
Making it easier for companies to access their data