When its internal policy experts were stretched too far, AI and machine learning cloud-based chat engines came to their aid.

How do bank policy experts cope with the extreme burden of fielding endless enquiries on risk management, financial regulations and banking rules every day?

Because questions can come from all over the world, naturally there can be delays due to time zone differences and individual workloads. And, depending on the day, people’s responses can vary.

One international bank decided to reduce the level of variance and dependencies in the work of its policy experts. Steve Suarez, HSBC’s Global Head of Innovation, Finance & Risk and Gareth Butler, Head of Risk Transformation and innovation Lead (Asia Pacific), decided to use AI to take a fresh approach to operational risk and resilience. The goal would be to answer questions faster and to improve the overall consistency and quality of policy response.

Search-enabled Chatbots

The bank envisioned building a solution that would support its large-scale, global environment. After evaluating the main AI solutions on the market, it decided on Google Cloud for the project, leveraging their existing strategic relationship.

The result was the Operational Resilience and Risk Application (ORRA), the first of what HSBC hopes will be many FAQ and document search-enabled chatbots.

ORRA performs dynamic document search and powers natural conversations. Easily accessible to all employees from the HSBC intranet, ORRA answers queries on internal policy and framework areas applicable across the bank. With this function powered by Google Cloud Dialogflow, HSBC was able to build a conversational platform that quickly and accurately addressed user needs at scale.

How was this done? First, the initial knowledge base consisting of intents, utterances, and answers was created. The content is then uploaded into the Dialogflow console. Various human-like features such as creating small talk and natural language processing (NLP) were added to humanize the bot responses. Through a friendly user interface, HSBC staff can ‘converse’ with a robotic policy expert for answers instead of a human expert. Users can now get direct answers when they interrogate the bot to scour through large documents for supplementary answers—within milliseconds.

Machine learning for decision making

According to Suarez: “Before the FAQ chatbot, somebody would ask you a question and if you didn’t know the answer or you gave an inconsistent answer, you’d have to do a bit of research and then come back to them. People go out and use Google to answer questions every day and receive instant, precise responses. Similarly, we’re now getting information to users in a way that feels familiar to them without having to read through an entire policy document.” Suarez said this gives risk managers access to immediate, accurate policy information and frees up time for subject matter experts to focus on adding value in less routine areas of their jobs. “It’s about the speed of getting your information,” he added.

Continually, the knowledge gained from analyzing the type, frequency, and source of queries is in itself valuable business intelligence on internal demands for information: “ORRA learns from every conversation, and at the most basic level, the more questions employees have about a specific policy, the more likely that policy may be due for simplification or revision,” Suarez said.

Added Butler: “In addition to providing rapid access to information, ORRA also brings important benefits for learning and development and the embedding of policies and procedures” said Butler. “As query flow increases, the architecture uses machine learning and user feedback to determine the best response to give.”

Scaling up this automation

Future versions of ORRA will include guidance on judgment calls. Said Chris Wilson, Head of Architecture, Policy & Regulatory Mapping at HSBC: “As we move forward, we’ll be adding in more around risk acceptance, risk issue, and risk relevance.

The next evolution of the FAQ chatbot will involve scaling the architecture to capture other policies and procedural data. Said Butler: “This is only the beginning of our conversational AI journey. The solution can accommodate more policies and documents; it can also be enhanced to support multiple languages, mobile interactions, and speech and can search numeric as well as text-based data stores. This opens up more possibilities in this space as more information is hosted on the cloud.”

Having invested the resources to develop and implement ORRA, the bank believes future expansion will be simple, cost-effective, and set the stage for implementing in other operations. Given the pervasiveness of chatbots across all areas of our lives, Suarez said this as an imperative for the bank: “In the future, we are going to be interacting with chatbots frequently for routine transactions. HSBC is taking the first steps in using cloud-based chatbot technology to get fast, accurate answers to our customers.”