• Innovation & technology

AI at BNP Paribas #2: analyzing telephone conversations with  BNP Paribas Cardif customers to improve service quality

Published On 06.02.2025

BNP Paribas has been integrating artificial intelligence into its tools and processes since 2016. More than 800 use cases are already in production. In this episode of our new series on AI at BNP Paribas, we focus on the “Call Analyzer” solution implemented by BNP Paribas Cardif, the insurance subsidiary of the BNP Paribas Group, to improve customer satisfaction.

Telephone conversations provide valuable information

More than 20 million customer phone calls are handled by BNP Paribas Cardif (Investment & Protection Services division within the Group) and its partners every year. The content of these conversations provides valuable data to help us better understand the areas for improvement in both the customer journey and the products or services offered to them.

Before artificial intelligence came along, the ability to listen to these calls was limited and time-consuming: at least 30 minutes of listening and analysis for a 15-minute telephone call. With AI, these conversations can be analysed rapidly over a wide scope and with unparalleled precision! For example, BNP Paribas Cardif in Peru successfully analyzed over 10,000 calls in 3 months.

What is this AI-based solution for analysing phone calls?

Call Analyzer is a solution developed by the Analytics and IT teams at BNP Paribas Cardif. Via an API (Application Programming Interface), Call Analyzer receives audio files and transcribes them into text using so-called “Speech to Text” artificial intelligence models. Then the solution uses AI to analyze the content of these transcripts by looking at vocabulary, speed of speech and lexical field, etc. This makes it possible to automate analysis of this conversation and so gain a better understanding of customer expectations during these calls, in a bid to determine any areas for improvement and also to ensure that a new product subscribed to by a customer corresponds to their needs. Call Analyzer ultimately generates statistics and verbatim comments that can be used to create dashboards

How can analysis of collected data enhance the customer experience?How can analysis of collected data enhance the customer experience?

This information is then used by different teams, including those in marketing or customer operations, in order to tailor service strategies to the customer in a more precise and responsive manner.The dashboards generated in data visualization tools enable the BNP Paribas Cardif teams to monitor key performance indicators and take rapid action in full knowledge of the facts.

The use of the information obtained in this way makes it possible to both:

  • optimise processes to speed up and simplify taking out insurance over the telephone, thereby improving customer satisfaction
  • improve products by analysing policyholder feedback, such as reasons for cancellation.

Beyond these targeted improvements, these analyses can be used more broadly in order to: 

  • perform in-depth assessment of customer opinions on services, in addition to NPS (Net Promoter Score) surveys which allow us to gather customer feedback after a key experience (“moment of truth”), thereby identifying the strengths and areas for improvement in our services and defining appropriate internal action plans
  • strengthen the customer loyalty strategy
  • fine-tune sales training in assessing customer needs and proposing products or services that match their needs.
The Call Analyzer solution represents a paradigm shift in how BNP Paribas Cardif leverages AI so as to better understand customer needs and challenges and increase customer satisfaction.

Jérôme Sarrail

Analytics Manager, Head of Call Analyzer, BNP Paribas Cardif

What are the upcoming developments?

The Call Analyzer solution is currently used in several Latin American countries and being deployed in other countries, especially in Europe. Call Analyzer now uses some of the capabilities offered by generative AI. Other features are being explored, such as the power of Large Language Models, which make it possible to generate even more detailed analyses of the information collected.

Keep in touch and receive our newsletter!

Select your topics of interest and frequency of delivery.