Inspiration

Customers get the first impressions about a bank during the onboarding process. Customers are likely to stay for a longer period when they realize the speed & convenience of the onboarding process.

Banks invest from as little as a hundred dollars to 20,000 dollars for each customer, they onboard. To reduce acquisition costs, going digital is the most economical solution of all.

Usually, the customer onboarding process takes a few days to even a few weeks. When the onboarding is confusing and takes too long.

In order to deliver a customer-first experience, a bank must clearly identify the key areas of friction using highly granular customer insights and deliver personalized onboarding communications based on customer needs at every relevant step.

What it does

Reduce the cost of onboarding significantly by introducing these procedures via mobile and a desktop– the experience has to be continuous in such a way that a customer can start this procedure on a mobile phone at the coffee table and finish onboarding on a laptop at work (at their own convenience). Being simple to use is critical when it comes to acquiring a new customer.

Being consistently present at multi-channels and an effort to avoid asking repetitive questions can help customers view this as a single process. Also, the need to eliminate broken/disconnected processes and provide transparency in terms of the number of steps and documents required must be mentioned upfront.

Offering to onboard customers via web, mobile, in-person or a call center can help improve overall satisfaction.

How I built it

This a prototype of how the application would look like. The application will use various machine learning models for different prediction tasks and verification. Twilio mobile API for verification.

Challenges I ran into

Finding and Identifying the suitable tools for Parsing ID, ID verification and classification, Face verification, Face alignment, etc.

What's next for Real-time Zero Risk Customer On-boarding

To integrate machine learning models for face verification, Google OCR integration to parse customer details and pass them through a validation system and anti-money laundering system.

Built With

Share this project:
×

Updates