# How IFFCO-Tokio uses H2O.ai

**$1M**: “The fraud use case saves IFFCO-Tokio more than $1M USD, roughly 70M INR, every year.”

As published on [h2o.ai](https://h2o.ai/case-studies/iffco-tokio-h2o). Captured by usedby on 2026-10-24.

- Company: [IFFCO-Tokio](https://www.usedby.ai/companies/iffco-tokio.md)
- Tool: [H2O.ai](https://www.usedby.ai/tools/h2o-ai.md)
- Industry: [Insurance & InsurTech](https://www.usedby.ai/companies/industry/insurance-insurtech.md)
- Teams: Claims, IT

## The use case: how IFFCO-Tokio deploys H2O.ai

IFFCO-Tokio, a general insurer, deployed H2O AI Cloud on-premise and used automated machine learning to build fraud detection models that score motor insurance claims by fraud probability. It later built a second model for health insurance claims.

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

> The fraud use case saves IFFCO-Tokio more than $1M USD, roughly 70M INR, every year. The models flag 100x more confirmed fraudulent claims each month than before, letting officers concentrate on high-probability cases while genuine claims move faster.

- **100x**: “The models flag 100x more confirmed fraudulent claims each month than before, letting officers concentrate on high-probability cases while genuine claims move faster.”
- **3 percent**: “Within one month, customer retention rose 3 percent.”

> H2O AI Cloud is a platform that my team can learn by themselves. I find the platform to be very friendly for people who are not data scientists or have little knowledge of data science.
>
> Seema Gaur, Chief Information Officer and Head of IT, IFFCO-Tokio

Source: [h2o.ai](https://h2o.ai/case-studies/iffco-tokio-h2o), captured 2026-10-24.

## H2O.ai users in Insurance & InsurTech

- [Jewelers Mutual](https://www.usedby.ai/companies/jewelers-mutual.md) — Observed
- [Nationwide](https://www.usedby.ai/companies/nationwide.md) — Observed
- [Progressive](https://www.usedby.ai/companies/progressive.md) — Observed
- [State Farm](https://www.usedby.ai/companies/state-farm.md) — Observed
- [Tokio Marine](https://www.usedby.ai/companies/tokio-marine.md) — Observed
- [Zurich Insurance](https://www.usedby.ai/companies/zurich-insurance.md) — Observed

## What usedby checked

We compared the story with its live page on 2026-10-24.

- Checked: the figure $1M is printed word for word on the page, near the name of IFFCO-Tokio.
- Checked: the passage quoted above is copied word for word from the page, near the name of IFFCO-Tokio.
- Checked: IFFCO-Tokio uses H2O.ai. Confirmed line. Latest check across sources: 2026-10-24.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/iffco-tokio-h2o-ai · How we check: https://www.usedby.ai/methodology