Valvoline Inc. · Abnormal Security
2 — Legacy email security solutions replaced
Vendor-reportedRetail & e-commerce · Fraud detection · Classical ML · In production
Fraud detection
Domino's · Abnormal AI
Vendor-reportedRetail & e-commerceUnited StatesIn productionEnterpriseClassical ML
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by abnormal.ai (vendor self-report). Checked against the source page on 2026-09-06. 1 of 1 figures below appear on that page word for word.
The problem
Domino’s had a secure email gateway (SEG) that didn’t stop advanced spear phishing, BEC, and account takeover attacks, leading to security analysts spending excessive time investigating malicious emails.
What was deployed
- Vendor
- Abnormal AI
- Products
- Abnormal
- Technique
- Classical ML
- Build or buy
- Bought off the shelf
- Deployment
- API
- Data used
- emails, conversations, business practices, other SaaS applications
- Scale
- 4,400+ Protected Mailboxes
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
41 hourstime saved on manual email investigations and remediationper day
“By saving the security analyst team 41 hours per day on manual email investigations and remediation, Abnormal has enabled Roeser to pivot the analysts onto more critical security needs.”
Quoted word for word from the source
“Human behavior has always been a big email security factor that attackers exploit. With Abnormal’s behavioral AI keeping attacks out of end users mailboxes, human error risks are reduced and we’re much more secure.”
Difficulties and limits
- A team of six security analysts was spending an outsized amount of their time investigating and responding to system and user-reported emails, receiving 500 tickets a day regarding potentially malicious emails.
- New AI-generated attacks were exceeding the ability of even security analysts to spot them.
Sources
- abnormal.ai — vendor self-report
Similar deployments
Perry Ellis · Yotpo
1.4% — conversion rate
Independently reportedRetail & e-commerce · Customer support · NLP · Scaled
Amazon · Amazon
10% more — shopper spend
Independently reportedRetail & e-commerce · Process automation · Computer vision · Scaled · 2024
Zalando
increased by 40% — basket sizes
Independently reportedRetail & e-commerce · Personalization · Classical ML · In production
Walmart · Microsoft
22% — global ecommerce growth
Independently reportedRetail & e-commerce · Search & retrieval · LLM · In production · 2024
Kingfisher Group
more than 10% — e-commerce sales originating from product recommendations
Independently reportedRetail & e-commerce · Personalization · Classical ML · Scaled · 2023