SPF Private Clients launches AI mortgage adviser

Ryan Bembridge

February 14, 2019

SPF Private Clients has developed Ava, an ‘AI virtual Help to Buy mortgage adviser’ which offers first-time buyers round-the-clock support for queries and a mortgage indication in three minutes.

Ava was created from IBM Watson and IBM Cloud and has been designed to handle enquiries from first-time buyers looking to take advantage of the Help to Buy scheme.

SPF noticed an increase in enquiries for Help to Buy over the weekend and late on Sunday evenings, which motivated the broker to develop Ava.

Freddie Savundra, digital architect at SPF Private Clients, said: “Lots of people want help understanding how much they can afford through the Help to Buy scheme and how each stage of the mortgage application process works.

“With Ava, we can guide them at every step, giving them confidence that they’re in the best possible hands.

“Combining live and bot chat allows us to elevate the client experience and manage a number of different client scenarios within one user-friendly interface.”

Ava answers customer questions, verifies personal details and documentation while processing enquiries at a faster rate.

SPF claimed this allows brokers to secure some of the best available lending rates and spend more time with clients.

Ava is powered using IBM’s Watson Assistant, an AI-enabled virtual assistant, and is built on the IBM Cloud.

The virtual adviser is trained on 200 common questions regularly received by the advisers and knowledge from the Certificate in Mortgage Advice and Practice (CeMAP). It offers quick clear answers that help guide buyers through the early stages of the buying journey.

Buyers can now get a mortgage recommendation in three minutes, a Decision in Principle in 15 minutes and be connected to an adviser for a full mortgage recommendation in 30 minutes, a service previously taking up to five working days.

The solution is integrated with IBM Watson Tone Analyser and Escalate AI solution, from IBM Business Partner Escalate AI, which allows it to analyse tone and confidence in client messages.

Over time and with built-in machine learning functionality, the virtual assistant is said to get smarter and better at advising on Help to Buy mortgages. As new questions come in, Ava alerts the advisers who can jump in to connect with the client the AI adviser remembers the answer for next time.

Ava was also developed using additional services on the IBM Cloud, including IBM Cloud Foundry, IBM Compose for MongoDB and IBM Cloud Object Storage. This has enabled the customer’s personal information to be securely managed.

Richard Voaden, channel leader, Watson and Cloud Platform, IBM UK and Ireland, said: “With the increasing digitisation of the mortgage market and more people seeking mortgage information and application processing online, Ava delivers real competitive advantage and expertise in simplifying the house buying process.”

Sign up to our daily email