Check out the on-demand sessions from the Low-Code/No-Code Summit to learn how to successfully innovate and achieve efficiencies by upskilling and scaling citizen developers. watch now.
Phone banking is beginning to revolutionize personality, thanks in large part to artificial intelligence (AI) and conversational artificial intelligence.
The first generation of phone banking was largely driven by Interactive Voice Response (IVR) technology. This is the touch tone-driven touch technology that delivers the monotonous beep asking you to “Pay 3 to get your bank balance”. Interactive Voice Response (IVR) is a technology that nobody ever liked, but it has done the job for many banks around the world for decades, albeit in a sub-optimal fashion.
A new, more modern approach is now beginning to emerge with capabilities such as voiceprint authorization, which provides a fingerprint-like feature that enables a user’s voice to authenticate into the system. The buzzing machine sound of IVR and the frustrating experience of pressing buttons to access multiple menus is also starting to come to an end with the help of an AI-powered customer contact center platform.
WaFd, formerly Washington Federal, is one such financial institution that is now using Amazon Lex conversational AI technology to help revolutionize how they do phone banking. WaFd is headquartered in Seattle, Washington, and has more than 200 chapters in eight states. The company has built its own digital enablement organization, Pike Street Labs, to help drive technology initiatives forward.
Smart Security Summit
Learn about the critical role of AI and machine learning in cybersecurity and industry-specific case studies on December 8th. Register for your free traffic pass today.
For WaFd, the move to conversational AI was also a way to help improve the user experience by helping customers get the information they want faster. Dustin Hubbard, chief technology officer of 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 press a button to actually get their balance.
“Now when you call, the system knows if your voice is authenticated, which means you can prove your identity,” said Hubbard. It says “my voice is my password” and the system responds “great, how can I help you?” At this point, you are having a conversation with the chatbot directly.”
Instead of the user needing to go through the IVR menu to get to the right place to be able to tell which button to press to get what they are looking for, the customer just has to ask for 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 legacy IVR system.
The ability to authorize voice typing comes from Talkdesk, which has a cloud-based call center as a service offering. Hubbard explained that when a customer calls a WaFd bank number, the call is picked up by the call center system. The voice authentication system verifies the user’s voice, as well as analyzing the phone number and location the call is coming from, before granting access to the account. The call center system can then log into WaFd’s online banking system through a series of APIs.
Once you sign in, Amazon Lex’s conversational AI technology kicks in. Amazon Lex is the conversation-based AI technology behind Amazon’s Alexa voice assistant. Amazon’s Lex service knows that a user has been authenticated and will allow users to simply request a balance check or make a cross-account transfer.
Although 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. In order to enable seamless integration, especially in terms of the actual audio users will hear, WaFd uses Amazon Polly technology.
Amazon Polly provides the text-to-speech capability that WaFd used to record the audio prompts that a user would hear in the Talkdesk system when initially connected. WaFd uses the same voice with Amazon Polly that it uses 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 sayings to train conversational AI
Training Amazon Lex on the banking use case of WaFd didn’t require an enormous amount of effort.
Hubbard explained that Amazon Lex was trained in a method known as speech. For example, by giving the system the phrase “check balance” and changes that users would use in a normal call, the system is instructed to check the balance of the user’s account.
Over time, Amazon Lex is getting better at inferring what the user’s intent is. For example, if the user doesn’t say exactly what speech has been trained, the system will be able to infer the probability that it is close, and it will still perform the expected action.
“This is how the conversational part of the AI is better with Amazon Lex than with a lot of other systems I’ve seen, where if there’s no perfect match, the thing simply has no idea what you’re talking about,” Hubbard said. “You can say, ‘Show me the money,’ for example, and the system will know you want to check your balance. Overall, over time, pattern recognition gets better.”
VentureBeat’s mission It is to be the digital city arena for technical decision makers to gain knowledge about the technology of transformational and transactional enterprises. Discover our briefings.