Data Co-op Update Logs - Issue #32

Nick Weldon

Sep 6, 2023 • 2 min read

Note from the Founders:

“August was a busy month, the team rolled out a brand new product (Email Validation), completed our new Company ID 1.0 (cc_ID) model, and added two key new features (work & education history) to B2B. Excited to share details!

OVERVIEW & KEY HIGHLIGHTS

The September product release is focused on improving data quality, firmographic entity resolution, and exposing new work and education history features.

Type	Item	Products Affected	Notes
New Product	email_validation	Email Validation Export	5x5 has productized tens of billions of observed email opens, clicks, and bounces into a 1B+ unique email monthly delivery.
New Feature	work_history	Universal Person, B2B Contact	This field is a JSON formatted work history, which includes data for: company_name, position, duration, start_time, end_time, job_description, location, and social_url.
New Feature	education_history	Universal Person, B2B Contact	This field is a JSON formatted education history, which includes data for: degree, description, start_time, end_time, institution_name, and social_url.
New ML Model	Company ID (cc_ID)	Universal Person, B2B Contact, IP2Company, Firmographics	The cc_id model establishes a parent record from a cluster of similar company records, based on a programmatic analysis of observed data, company and contact data, web-redirections, and geo-spatial signal analysis. The cc_id provides members with high quality firmographic domain linkage.

PRODUCT DEEP DIVE

NEW PRODUCT DETAIL: Email Validation

For the last two years, the Co-op has been observing tens of billions of email validation signals, linking all common hashes and last seen / validation statuses into a single record for each email. Now for the first time, we are productizing access to this data asset and will be updating it on a monthly basis.

Schema: docs.5x5coop.com/docs/email-validation
To date, we've observed 1.01B unique emails with a validation status

NEW MODEL DETAIL: Company ID (CC_ID)

The Co-op leveraged the ML models from up_ID to improve the quality of firmographics 3.0. The higher quality firmographic linkage provided by the cc_ID will improve the entity resolution in the IP2Company and increase the quality within the UP and B2B contact files.

Here is an example of how the new model rolls up different domains within the Walmart Corporation:

Before cc_ID:	With cc_ID, parent domain identified as:
walmartcareers.com →	walmart.com
careers.walmart.com →
walmart.com.br →
walmartlabs.com →
walmartmedia.com →
walmartstores.com →

WHAT WE’RE WORKING ON

Launching the beta program for the new categorical Intent Stream later in September
Adding company and bio descriptions to UP and B2B exports
Improving entity resolution and linkage in UP model 2.0
Expanding Primary_Industry codes from 148 to 420 categories

*Let us know if you have any questions on the items above and if there are any priorities you’d like added to this list.

If you are subscribed to the B2B, Universal Person, IP2Company, or IP2HEM exports, you'll receive a separate email with the bucket locations.

Please email nick@5x5coop.com if you have any questions regarding the most recent data delivery updates and if there are any data projects or issues that you’d like to see prioritized that we haven't mentioned.

We appreciate all your feedback,

Nick Weldon, Founder of The Data Co-opP.S. for the full schemas, feature counts, and fill rates, visit docs.5x5coop.com.

OVERVIEW & KEY HIGHLIGHTS

PRODUCT DEEP DIVE

WHAT WE’RE WORKING ON

Sign up for more like this.