Where Does Our Data Come From?
Steppingblocks pulls from hundreds of publicly available sources to compile and process over 1 billion data points and career milestones. The result: data on 150+ million profiles, covering more than 90% of the active U.S. workforce.
Here's how it works.
Data Acquisition
Everything starts with collection. Steppingblocks acquires data from hundreds of publicly available online sources into our data lake, including but not limited to:
Resumes posted online
Job and skills data from public social media profiles
Company bios, directories, and contact information
Employment and federal databases
Skills and certifications data
Labor market and job postings data
Data Processing
Once collected, we have over 1 billion raw career milestones to work with. From there, our team runs the data through a rigorous validation and machine learning process. Some examples of what happens in this phase are:
Deduplication, profile merging, and version control
Accuracy testing, human audits, and certification
AI and machine learning handle quality tagging, advanced modeling, and data derivations including salary predictions.
Any anomalies flagged along the way go to human review before the data moves forward.
What do we require from you?
Nothing beyond your school's academic catalog, which we use to match major names and programs to our data.
How often is the data updated?
Quarterly, so you're always working with current information.