Customer Identification & Fraud Detection from Maruti Techlabs' Playbook: A Banking Case Study

Expertise Delivered

Product Development & QA

Industry

Banking

Client Brief

The client is a prominent banking group in the UAE established in 1985, known for its diverse services and products: private banking, commercial banking, wealth management, corporate banking, foreign exchange, project finance, property management, and more.

With an aspiration to be the #1 bank in the UAE, the client, with an employee base of 5,000, offers its products and services to over 1 million customers.

Project Scope

The client used Interactive Voice Response (IVR) and agent call routing to address customer queries and conduct transactions. The existing system was time-consuming for customers and agents and posed a significant challenge from the perspective of potential fraudulent activities.

To circumvent this challenge, they decided to implement a voice-enabled system to enhance security and verify caller identities during customer calls and transactions.

Once the caller's identity is confirmed, the caller can access multiple banking services, such as adding beneficiaries, money transfers, and more - all through voice commands.

Based on the discussions between Maruti Techlabs and the client, both teams narrowed down the scope, which covered the following -

• Use voice biometrics to improve security and speech authentication success rate
• Design a platform that facilitates future voice-recognition integrations, like all branch transactional activities
• Automate call routing and common customer requests to reduce the workload for call center agents while enhancing customer experience

Challenge

It’s standard practice for banks to conduct their customer due diligence (KYC) process before offering services. The KYC process primarily includes document verification, such as utility bills, address verification, and biometric verification. Hence, it's easy for agents to learn the specifics of a call for an inquiry or request.

However, it's challenging for agents to determine the identity of the person conversing on the other side of the call. Due to this predicament, the customer authentication process consumed agents' time without offering a foolproof system to identify fraudsters against genuine customers.

Fraudsters today have numerous tactics to learn a customer's identity and confidential information. The client wanted to introduce automatic voice recognition to offer safer and quicker means of conducting bank-related transactions.

The key goals were to overcome challenges such as decreasing the turnaround time (i.e., 45-60 seconds/customer) for authenticating customers on calls, offering effortless voice authentication instead of PIN authentication, and mitigating fraud risks from compromised customer information through social engineering and phishing.

Solution

Passive voice biometrics leverages voice recognition technology to identify individuals based on their unique vocal characteristics when speaking passively or naturally. To achieve this, our team designed a web portal that would seek consent from customers to create a voice pass, enroll the voice pass on the IVR, and register the customer once their voiceprint is generated.

We designed a two-part solution covering a voiceprints management portal and a fraud detection application. Here's a brief overview of the implemented solution -

1. Voice Biometric Enrollment

Human ears cannot perceive subtle traits that help recognize the human voice. But biometric solutions powered with artificial intelligence can do this effortlessly. To design this solution, we deployed a voice recognition platform that compares a caller's voice with a passive voiceprint stored in the database.

A passive voiceprint is a mathematical impression of a customer's voice created during the initial interaction with the platform. Once a customer's real-time voice finds a match with the passive voicepass in the database, the platform apprises the agent that the caller has been verified.

We implemented the voice recognition solution using Phonexia (a voice biometric and speech recognition software). Our foremost task with new speakers was to add their voice samples to the database to identify them and eventually leverage them to train the voice-assisted self-service model.

Designing the voice identification and enrollment process involved the following steps:

1. The Agent receives a call from a particular number.
2. The system checks if this is an already existing contact or a new caller.
3. The system examines audio for an existing contact and compares it with the registered voice biometric.
4. If the voice matches the registered passive voice biometric, the user is authenticated to access bank services.
5. If the system doesn't authenticate the caller, the system guides the agent to ask security questions.
6. Users are authenticated if they answer the security questions correctly; otherwise, the system marks the caller as a fraud.
7. New speakers with unregistered passive voice print are asked for consent to enroll.
8. Agents observe the customer ID and consent to enroll on the ITQAN CRM.
9. Collect a 20-second voice sample using Phonexia.
10. The collected voice print is passed to the Admin to enroll the voice sample in the speaker's tab.
11. Admin assigns a Speaker ID and a Voiceprint ID at enrollment time.
12. The speaker tab includes customer ID (CID), registered phone number, first and last name, voiceprint ID, and voiceprint status (Active-Inactive-Locked).
13. Admin can sort or search for a particular voiceprint using the CID, voiceprint status, date of creation, and date last used.
14. The speaker's tab doesn't reflect confidential bank details such as account numbers, answers to authentication questions, addresses, etc.

2. Fraud Detection

Fraudsters have a bag full of tricks that can deceive even the most experienced customer care representatives. For most agents, it’s difficult to perceive that they’re being victims of fraud.

The voice portal would learn verbal cues from the caller’s voice, compare it with the unique traits in the voice sample saved from passive voice biometrics, and alert the agent about the suspicious demeanor of the call.

Any suspicious callers would be added to a distinct repository. These voiceprints would eventually be used to educate the voice recognition model on how to spot and flag similar future interactions.

Communication and Collaboration

Our commitment to grasping their project requirements, the approach towards solutions, and implementation, coupled with our previous engagement for a chatbot and live chat project, paved the way for the client to partner with us again.

The initial estimation of the project timeline was 3 months, but it was extended to 4 months due to evolving client needs.

The development phase started with weekly meetings to share a broad overview, which then switched to daily scrum meetings to ensure detailed coordination between both teams.

We deployed a dedicated team of engineers covering -

• Backend Engineers
• Frontend Engineers
• QA Engineers
• Technical Lead

Our development team was skilled, communicative, and adaptable to meet the client's needs for a successful project.

We held daily standup meetings for progress monitoring and used Microsoft Teams for feature rollouts, client queries, and sprint reviews, with everyday communication managed through Slack.

We utilized Jira for transparent progress tracking, enhancing productivity, and streamlining processes to meet project goals and deliverables efficiently.

Technology Stack

Results

The voice portal, developed by Maruti Techlabs, significantly benefited our client by offering real-time voice-enabled protection and transactional services. This transformation has resulted in a remarkable 36% increase in the first call resolution rate and an impressive 52% enhancement in the customer satisfaction score.

• Simplified authentication with passive voice biometric recognition, eliminating the need to remember passwords or critical phrases.

• Streamlined customer interactions by offering personalized greetings, appointment scheduling, transaction assistance, complaint resolution, and more.

• Introduced remote identity verification for agents working remotely to protect clients' and companies' confidential data.

  
  

The client adopted a secure AI-powered voice-based system to optimize customer call handling. This solution has significantly improved their operations, exemplifying its effectiveness in elevating customer service and satisfaction. The net result has been the fortification of anti-fraud initiatives and automated verifications, which has seen a significant boost in the overall customer experience.

Our Development Process

We follow Agile, Lean, & DevOps best practices to create a superior prototype that brings your users’ ideas to fruition through collaboration & rapid execution. Our top priority is quick reaction time & accessibility.

We really want to be your extended team, so apart from the regular meetings, you can be sure that each of our team members is one phone call, email, or message away.

Why Choose Maruti Techlabs?

The client wanted to bring on a partner with expertise and experience in working with voice recognition technology. To our benefit, we had previously collaborated on building and successfully delivering a chatbot solution for one of their projects.

Upon completing the RFI phase, we were shortlisted amongst five other product development partners from Greece and India for the RFP. Outside of the qualification criteria set within the RFI and RFP, Maruti Techlabs was shortlisted due to its previous relevant experience in building similar solutions, customer references, and long-standing relationships with the clients themselves.

With the first objective being a detailed discovery phase, we comprehensively understood the client’s technical, functional, and business requirements. The entirety of the project was meticulously documented in a clear and structured manner, leaving a positive impression on our client. As a result, they decided to move forward with the development phase.