8 ways NLP can help to deal with a vulnerable customer

Written on
byKatie Hunter

In this digital age, technology is making our lives easier in many ways, from asking Alexa to add milk to your shopping list, Netflix suggesting a new show it thinks you’ll love and even self-driving cars.  Technology in the workplace has made employees more productive than ever before by streamlining tedious processes, making working from anywhere, anytime possible and connecting people instantly.   Firms are welcoming ways technology can assist in making previously problematic tasks easier and more efficient.  One way that Aveni is making a difference for regulated industries is to help with the challenge of how to deal with a vulnerable customer experience. Here we look at how much of an impact our platform can have on companies, agents and customers.  



1. Not many customers will declare they’re vulnerable during a conversation with a customer agent.  Elderly people in particular are often reluctant to disclose sensitive information for fear that it will impact their chance to access a particular service or product.  Others might feel embarrassment or shame and not wish to draw attention to it.  Speech analytics can help recognise vulnerabilities by monitoring and flagging not just keywords and phrases, but also patterns and sentiment that indicate vulnerability.  We’ve trained our models with thousands of real life examples, incorporating classifiers of vulnerability including caring responsibilities, physical disabilities, long-term illness, financial issues and mental health concerns to extract indicators of these vulnerabilities.  When any of these indicators happen within a conversation, a vulnerability is flagged.  Knowing that every call is being assessed, providing 100% coverage, gives comfort that every vulnerable customer will be looked after, not just the ones randomly selected. 


2.  Aveni Detect goes further by not just flagging risk, but ranking it and pinpointing the exact place in the call that assessors need to look at, improving prioritisation of those most in need.  We work with partners to tailor their prioritisation of vulnerabilities.  Certain vulnerabilities will always be high, suicidal indicators being the most obvious example, but others differ between organisations.  In a high street bank, someone over 70 may be flagged as vulnerable due to their reduced ability to use digital products however, in an equity release company where a target customer demographic is later life, it would be unhelpful to identify every customer as vulnerable so they might place a lower prioritisation on age.  The outcome is we tune our risk ranking to align to specific customers, allowing firms to ensure limited resources are focused on their priority cases.  


3. Vulnerabilities can be very nuanced and complex, often one can lead to another.  The ability to capture 100% of customer information gives a more thorough understanding of an individual customer’s situation.  Typically in a manual QA review, the assessor would assume to have captured a vulnerability after reaching the point in the call where it becomes apparent.  Aveni Detect will flag all points of a call deserving of further attention which produces a more detailed picture of how to deal with a vulnerable customer and the support they may need.  


4. Only 12% of advisors find vulnerable customers easy to identify which means better agent training and support needs to be implemented.  Connecting machine driven assessment of what vulnerability looks like with Learning & Development can significantly drive agent performance and enable more effective and continuous improvement of your agents. For example, an agent who has shown a lack of empathy on multiple calls would be recognised, resulting in the appropriate training materials being flagged for improvement.  Importantly, all of this activity can be recorded and tracked providing evidence that you’re creating the right environment and offering resources to agents for them to enhance their service.


5. Speech analytics can identify trends, pick up on indicators and get in front of emerging vulnerabilities in advance. This will allow companies to respond faster and in a more informed way, supporting contact centre agents with this information and providing additional training and resources. The COVID-19 pandemic is a good example of this – companies would have seen a significant increase in respiratory disease/health flags and higher rates of redundancy and perhaps made an assumption on the impact it was going to have on their business.  They could have rolled out policy changes on repayment plans, trained staff on how to react to the problems customers may be facing and anticipated changes in customer behaviour.  It is a huge ask to expect agents to spot and report new trends so it is unlikely that this would have been picked up as quickly using manual methods.    



6. Our algorithms learn from each customer interaction, embedding a process of continual improvement. We deploy a range of techniques to ensure our accuracy levels are constantly improving.  This means model performance evolves with your business and output continually improves over time.  But technology is only part of the solution and we firmly believe in Human+.  Our embedded learning means that human reviews carried out on the platform results in training data that will drive even more learning.  


The Future

7. We’re currently developing Aveni Detect, which is being used to assist with “real-time” conversations to help firms reduce exposure, supporting agents immediately. It moves our current second line control to AI-driven detection and prevention at the point of service. Aveni Detect will monitor live calls, flagging to agents where vulnerabilities emerge and to supervisors when critical issues are discussed in call. This increases the likelihood of better treatment of vulnerable customers and reduces the risk of poor conduct, customer experience and outcomes. 


8. The most important impact speech analytics can have is to ensure vulnerable customers get the outcome that meets their needs.  Working with other technology providers and charities we will aim to ensure agents are clear on the most appropriate course of action for each customer and use technology to transition vulnerable customers who need specialist support to sources e.g. Dementia UK or Samaritans, that can help.  As mentioned at the start, it’s difficult for most people to discuss their vulnerabilities with strangers and saving the discomfort of customers repeating themselves goes a step further in providing great customer service. 


To learn more about how you can work with Aveni and support customers in vulnerable situations, visit our customer vulnerability page

Other recent posts

Podcast logos-03

AI’ll Take Your Job

Join Joseph Twigg and Jamie Hunter, the dynamic duo of financial services and AI, as they unleash their wit and wisdom on the game-changing influence of recent AI development on the industry.  

Replay social 2-06

An Introduction to ChatGPT in Financial Advice

Our CEO Joseph Twigg was joined by Iria Del Rio, our lead NLP engineer to talk about the explosive rise of ChatGPT and other large language models, what got us here and what this...

Three confident business people having discussion while working in the office together

Beyond the basics: Debunking common QA assumptions in financial services

Quality assurance (QA) is a critical business function, ensuring that products and services are compliant with regulation and meet customer needs. However, there are some common assumptions about QA within the financial services industry...

Board member and FCA proposal

Aveni partners with Delta Capita to power their Consumer Duty offering

Aveni has partnered with Delta Capita, a leading global capital markets consulting, managed services and technology provider, to advance their Consumer Duty offering by providing their clients with access to our cutting edge AI...

limitation of ChatGPT in financial services

Limitations of adopting chatGPT and other large language models in the financial services industry

There has recently been a lot of hype surrounding ChatGPT, and other large language models (LLM’s) and rightly so. Their extensive capabilities make them impactful for a wide range of use cases across various...

It pays to plan properly for the future. Cropped shot of a senior couple getting advice from their financial consultant.

Age Partnership selects Aveni Detect platform to enhance customer outcomes and mitigate risks

Aveni.ai, has been selected by Age Partnership, one of the UK’s leading Equity Release Advisory firms, to revolutionise its Quality Assurance systems setting new standards for customer service and outcomes.     Following a successful...


Demonstrating Consumer Duty Compliance with Technology - Key Takeaways from Aveni’s recent webinar

In our latest Consumer Duty webinar series,”Demonstrating Consumer Duty Compliance with Technology,” Joseph Twigg, CEO of Aveni, sat down with John Liver, Strategic Adviser at Kore and NED at Barclays, and Alan Blanchard, Head...

Aveni SPW

Schroders Personal Wealth adopts AI-based Aveni Detect platform to transform compliance function

Aveni, has been selected by Schroders Personal Wealth (SPW) to transform its compliance function. Through the deployment of the Aveni Detect platform SPW will use the latest advances in Natural Language Processing (NLP) to...


Human in the loop 101: what is it and why is it so important?

Financial services firms have been turning to Natural Language Processing (NLP) solutions to extract valuable insights from vast amounts of unstructured data. But even the most advanced algorithms can’t match the intuition and creativity...