Skip to main content
usedby

As published on h2o.ai. Checked by usedby on Oct 17, 2026.

What happened

Airvantage uses H2O Driverless AI to build a machine learning model that scores airtime-advance credit risk for prepaid telecom subscribers in real time. It replaced a static rules-based scoring engine and re-evaluates customers the old rules had rejected.

Summary written by usedby from the source page, in English. The figures are those of H2O.ai and Airvantage, not ours.

Its static, rules-based scoring was overly defensive, turning away creditworthy customers, so the team evaluated more than 30 toolkits, ran POCs with four platforms, and chose H2O Driverless AI.

From the page. h2o.ai

With H2O Driverless AI's MOJO technology, we are able to integrate strongly with our current infrastructure.

Maram Mishan, Actuarial Data Scientist, Airvantage. Source

What the story claims, and what we checked

What we compared with the page.

  • The passage quoted aboveCheckedCopied word for word from the page, near the name of Airvantage.
  • Airvantage uses H2O.aiCheckedConfirmed line.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

70%“cut model development time by 70%”Acordo Certo uses H2O.ai. Another customer of H2O.ai$1M“saving roughly $1M a year”AES uses H2O.ai. Another customer of H2O.ai$10M“saves more than $10M per year”AT&T uses H2O.ai. Another customer of H2O.ai