Check out the on-demand sessions from the Low-Code/No-Code Summit to learn how to successfully innovate and gain efficiencies by improving and scaling citizen developers. look now.
Telephone banking is starting to take on a drastic personality change, thanks in large part to artificial intelligence (AI) and conversational AI.
The first generation of telephone banking relied heavily on Interactive Voice Response (IVR) technology. It is the touch tone based technology that provides the monotonous voice tone telling you to “press 3 for your bank balance”. IVR is a technology that has never been particularly liked by anyone, but it has done the job for many banks around the world for decades, albeit in a sub-optimal approach.
A new, more modern approach is now beginning to emerge with features such as voiceprint authorization, which provides a fingerprint-like function that allows a user’s voice to authenticate itself to the system. The buzzing machine voice of the IVR and the frustrating experience of pressing buttons to cycle through multiple menus are also beginning to come to an end with the help of an AI-powered customer contact center platform. .
WaFd, formerly known as Washington Federal, is one such financial institution that is now using conversational AI technology from Amazon Lex to help revolutionize the way it does banking over the phone. WaFd is based in Seattle, Washington, and has more than 200 branches in eight states. The company created its own digital enablement organization, known as Pike Street Labs, to help drive technology initiatives forward.
Smart Security Summit
Learn about the critical role of AI and ML in cybersecurity and industry-specific case studies on December 8. Sign up for your free pass today.
For WaFd, the move to conversational AI was also a way to improve the user experience by helping customers get the information they want faster. Dustin Hubbard, chief technology officer at WaFd Bank and Pike Street Labs, told VentureBeat that previously it took about four and a half minutes before a customer got to the point where they could push a button to get their balance.
“Now when you call, the system knows if you’re voice authenticated, which means you can prove your identity,” Hubbard said. “You say, ‘My voice is my password’ and the system responds, ‘Great, how can I help you?’ and at that point you are chatting directly with the chatbot.
Instead of the user needing to go through the IVR menu to get to the right place to know which button to press to get what they are looking for, the customer just has to ask what they want. Hubbard estimated that instead of four and a half minutes for a user to get a bank balance, they can now get it in about 28 seconds.
Several components of the WaFd platform have replaced the old IVR system.
The voice print authorization capability comes from Talkdesk, which offers a cloud-based call center as a service offering. Hubbard explained that when a customer calls the WaFd bank number, the call is picked up by the call center system. The voice authentication system verifies a user’s voice, as well as analyzes the phone number and location a call is coming from, before granting access to an account. The call center system can then connect to the WaFd backend online banking system through a series of APIs.
Once connected, Amazon Lex’s conversational AI technology kicks in. Amazon Lex is the foundational conversational AI technology behind Amazon’s Alexa voice assistant. Amazon’s Lex service knows the user is authenticated and allows users to simply request to check a balance or transfer between accounts.
Even though WaFd uses two systems, with Talkdesk and Amazon Lex, Hubbard said it’s completely transparent to users who don’t know they’re switching between systems. To enable seamless integration, especially in terms of the actual voice users will hear, WaFd uses Amazon Polly technology.
Amazon Polly provides a text-to-speech capability that WaFd has used to record voice prompts that the user will hear in the Talkdesk system on their first call. WaFd uses the same voice with Amazon Polly as with Amazon Lex. Hubbard said he wanted to make sure users had a consistent experience with the same voice.
Show me the money – how Amazon Lex uses utterances to train conversational AI
Training Amazon Lex for the WaFd banking use case didn’t take much effort.
Hubbard explained that Amazon Lex is trained with an approach known as utterances. For example, by giving the system the phrase “check balance” and variations that users might use during a normal call, the system is directed to check the user’s account balance.
Over time, Amazon Lex gets better at inferring user intent. For example, if a user does not say exactly what the formed utterance is, the system is able to infer the probability that it is close, and it will still perform the expected action.
“That’s how the conversational AI part with Amazon Lex is better than a lot of other systems I’ve seen, where if it’s not an exact match, the thing has pretty much no idea what you’re talk,” Hubbard said. “You could say, ‘Show me the money,’ for example, and the system will know you want to check your balance. And usually, over time, it gets better at recognizing patterns.
VentureBeat’s mission is to be a digital public square for technical decision makers to learn about transformative enterprise technology and conduct transactions. Discover our Briefings.