What challenges did KOHO face before AI implementation?

Traditional credit systems cannot evaluate credit-invisible customers. KOHO needed to reduce account takeovers in its app.

What was the impact of the AI solution?

Lent to customers at six times lower cost with loss rates six times lower. Cut account takeovers by about 70%. Enabled hundreds of thousands of Canadians to improve credit scores and lent hundreds of millions of dollars. Saved customers tens of millions in bank fees.

Source

KOHO: Generative AI on Amazon Bedrock for credit underwriting and fraud detection

Use case typeRisk assessmentUpdated 5 days ago

KOHO rebuilt credit infrastructure to assess credit-invisible customers using behavioral data such as rent, utility, and phone payment records. The company built Kortex AI on Amazon Bedrock to extract behavioral insight for underwriting and used AI screen detection to reduce account takeovers.

Organization: KOHO
Industry: Finance
Location: Canada
Published: July 2026

Reported outcomes

−70%

account takeoversOther quantified impact

6 x lowerlending cost6 x lowerloss rates

Strategic outcomes

Other strategic outcomeExpanded credit access for credit-invisible CanadiansCustomer experience & trustImproved fraud protection and transaction safetyCost efficiencyImproved team productivity

Primary read

Use case focus

Showing 3 of 3

1Risk assessment
2Fraud detection
3Decision support

Traditional credit systems cannot evaluate credit-invisible customers.
KOHO needed to reduce account takeovers in its app.

Consolidated heterogeneous behavioral data streams into a unified underwriting view.
Built Kortex AI on Amazon Bedrock to extract behavioral insight for underwriting at speed and scale.
Used AI-powered screen detection technology to identify account takeovers and protect users.

Technologies

Amazon Bedrock AWS compute AWS storage AWS data integration

Lent to customers at six times lower cost with loss rates six times lower.
Cut account takeovers by about 70%.
Enabled hundreds of thousands of Canadians to improve credit scores and lent hundreds of millions of dollars.
Saved customers tens of millions in bank fees.

Sources & evidence1

Groundedness: 5/5Type: Customer StoryPublished: Jul 8, 2026Publisher: AWSEvidence: PrimaryConfidence: High

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence