Improving Call Centre Performance and Customer Sentiment Analysis for First Central Group
FCG have a wealth of experience in leveraging data and their data sources in order to reveal trends, risk, and opportunity in the market. This approach to data analysis puts them in a unique position to influence the market and to develop a platform that puts transparency and accessibility right in the hands of their customers via their bespoke insurance platform.
Improving Call Centre Performance and Customer Sentiment Analysis for First Central Group
FCG have a wealth of experience in leveraging data and their data sources in order to reveal trends, risk, and opportunity in the market. This approach to data analysis puts them in a unique position to influence the market and to develop a platform that puts transparency and accessibility right in the hands of their customers via their bespoke insurance platform.
At a glance
First Central Insurance & Technology Group (FCG for short) is a fast-growing UK insurer and innovator in data, delivering market-leading motor insurance, underwriting, distribution, finance, technology and legal services.
Challenge
FCG were looking to find hidden value in their existing customer call centre data.
Solution
Using a Generative AI solution to leverage existing data, improving on NPS scores and identifying tactics, actions and behaviours that were impacting mid-term adjustment (MTA).
Services Used
Amazon DynamoDB
AWS Lambda
Amazon SageMaker
Outcomes
10x faster summarisations
300% more likely to provide accurate sentiment analysis
Business challenges
Always challenging the insurance market
Looking forward and recognising the trends around new AI and ML technologies, FCG has once again recognised an opportunity to further innovate. A new goal has been realised, though this time the source is not the market data available through public and 3rd parties, but in the customer data FCG holds around their own call centre and within thousands of customer feedback surveys.
“Firemind's PULSE tool was able to quickly and accurately summarise vast datasets of customer surveys, ensuring we could take action against any negative customer experience elements.”
Dean Macfadyen, Data Platform Engineer — FCG
Solution
Adapting our LLM tool to suit FCG
As part of Firemind’s suite of tools, we provided a fixed pilot Gen AI platform (PULSE) that envisaged the creation of a data platform, connected to data sources, that can be deployed into production.
The overall scope of works for this pilot Gen AI platform will provide three parts, delivered in succession, leading to the deployment of the pilot Gen AI platform as the following phases:
1. Deploy Firemind’s Gen AI sandbox.
2. Utilise Firemind’s professional services to run prompt engineering and data wrangling exercises.
3. Build out three focused use cases to help FCG achieve their aims and prove their hypothesises using data and AIML projects.
Fast summarisations
We saw 10x faster text summarisations of large datasets, ensuring a high level of accuracy against data garnered from call centre forms, surveys and feedback.
Accurate sentiment analysis
The tool was 300% more likely to provide accurate analysis of customer sentiment than any manual, human led analysis. Providing time saving potential for all human operators.
Why Firemind
“This was our first look into generative AI with AWS, and we were astonished by the fast results and summarisations using our own prompts."
Firemind was recognised as an excellent partner to explore this opportunity with AI and ML. The early engagement between FCG allowed Firemind to demonstrate the potential with a part of their toolkit; a GenAI Demo that uses a Large Language Model (LLM) to reveal trends and opportunities from customer feedback data.
This demonstration allowed FCG to see what possibilities exist for leveraging their own data to drive efficiency and agent performance. Connecting a similar solution to FCG call centre and customer data proved how Generative AI and ML can achieve their desired business outcomes.
1920%
Workflow speed increase
1,000 documents in 12.5 minutes compared to 4 hours by human operator
88%
Keyword accuracy
for leading categories within data modelling & training
Added value
We were also able to take all stakeholders on a journey concerning how Cloud Adoption and Machine Learning would benefit their customers and their business continuity, all in a 12 week timeline from start to finish.
Get in touch
Want to learn more?
Seen a specific case study or insight and want to learn more? Or thinking about your next project? Drop us a message below!