AWS Machine Learning Blog

Aella Credit empowers underbanked individuals by using Amazon Rekognition for identity verification

Aella Credit is a financial services company based in West Africa that provides instant loans to individuals with a verifiable source of income in emerging markets by using biometric and employer data.

For those in emerging markets, identity verification and validation is one of the major challenges for people who don’t have easy access to retail banking services. To help resolve this, Aella Credit uses Amazon Rekognition, a deep learning-based image and video analysis service, for biometric identity verification on their mobile application. Using Rekognition in the application allows customers to verify their identity and get access to banking services with minimal friction.

“The ability to properly identify users is a key hindrance in building credit for billions of people in emerging markets,” says Wale Akanbi, CTO and Co-Founder of Aella Credit. “Using Amazon Rekognition for identity verification on our mobile application has reduced verification errors significantly and given us the ability to scale.”

This feature enables customers to upload a photo of their government-issued ID and then take a photo of themselves in real-time for verification. Aella Credit first verifies the government-issued ID against the government database, and then uses Amazon Rekognition to compare the two images to see if they are a match.

“We can now detect and verify an individual’s identity in real time without any human intervention, thereby allowing faster access to our products,” says Akanbi. “Amazon Rekognition helped us effectively recognize faces of our customers in our markets. It also helped us with KYC [know your customer] in discovering overlapping profiles and duplicate datasets.”

 How it Works

  1. Customers take a profile picture to complete the application process
  2. Face is detected and application process is completed

“We chose Amazon Rekognition because of its ease of use and consistent accuracy,” says Akanbi. “We tried various well-advertised solutions, but none of the popular alternatives could accurately map out various skin tones. While other solutions would provide 40% accuracy for facial detection of our customers’ various skin tones, Rekognition consistently provides us with 90% accuracy—better than anything else we tested in the market.”


About the Author

Kaiser Larsen is a Product Marketing Manager for AWS artificial intelligence solutions. Outside of work you’ll find him hiking, cooking for family and friends, and eating ice cream whenever there’s an excuse to celebrate.