BNP Paribas Personal Finance: Fintech Chatbot Challenge

Serendip Fintech Accelerator Program

program-start-cropped

Key Facts

Fintech Program

  • The Serendip Fintech Accelerator Program was organised in partnership with Bruntwood SciTechBNP Paribas Personal Finance and SuperTech WM
  • Serendip is a program for financial startups and entrepreneurs to fast-track innovative ideas and expertise for the  banking and financial sector, improve financial processes, and provide economic opportunities for emerging fintech businesses.
  • The Bot Forge was selected alongside Credicar for the 6-month program to participate in Challenge 3 (Chatbots).

Customer

Corporate Challenge Partner

BNP Paribas Personal Finance

BNPP-PF-Cred

The Challenge: Chatbots

BNP Paribas Personal Finance set the following challenge:

"How might we best implement chatbots to make them successful for our customers and our business? This challenge is about how to easily create a conversational chatbot and IVR powered by AI to simplify the customer experience and be conscious about the design so that customers can actually complete what they want to do rather than adding another ‘’channel’’ into existing call centres."

The Project

Introduction

BNP Paribas Personal Finance (BNPPPF) is a subsidiary of BNP Paribas Group, a leading European bank. They offer a range of consumer lending products, such as personal loans, car loans, and home improvement loans, as well as insurance and savings products.

They have a presence in 30 countries and support more than 20 million customers daily. They offer online and offline services to provide a comprehensive and tailored experience to their customers.

Brief

Our brief was to work closely with the BNP Personal Finance customer support team on a website-based chatbot project.

The aim of the challenge was to focus on providing an understanding of conversation design best practices and workflows as well as to develop a functional proof-of-concept chatbot which would handle a selection of prioritized use cases from common existing customer support enquiries at BNPPPF.

Our Approach

Conversation Design Following Industry Standards

The challenge was to carry out a reduced-scope conversational AI project with a focus more on the process and industry best practices of conversation and NLU design than the final implementation of existing technologies of the BNPPPF technical landscape.

Discovery & Requirements

By carrying out a series of onsite workshops and twice-weekly virtual project meetings we carried out the following investigations and built up a solid understanding of BNPPPF technologies, operations and users.

Technologies

Explored the available technology landscape at BNP Paribas PF concentrating on the conversational AI capabilities of the current technology vendor at BNP Paribas PF.

We carried out a series of fact-finding workshops and meetings with the BNPPPF customer support team.

Operations

We looked at the BNPPPF customer support operations in more detail. In particular, we looked at support queries that the support teams are currently handling.

We were also able to gain a detailed understanding of specific transactional enquiries by following call flow diagrams and also support staff information flow cards for specific support enquiries.

User Personas

It's important to understand User/customer personas so we spent some time looking at the types of customers an automated solution would need to assist. Where the conversations would take place was also considered.

Users could be one of 2 types: existing users or new users.

Happy Conversation Design

Creating Chatbot Persona

For a chatbot persona, BNPPPF already had a character, Credito, so we were able to take the tone of voice and character traits from existing brand guidelines. The brand guidelines and tone of voice were then followed through in later stages when writing the chatbot responses.

Discovering & Prioritizing Use Cases

From the pool of use cases and support queries covered in the earlier discovery phase, we were able to agree on a subset of user journeys for existing and new customers which we could concentrate on helping with a chatbot.

  • Log in support
  • Repeat account details
  • Making a payment
  • Early settlement
  • Electronic signature

Security Considerations

It's no surprise that implementing a production-ready chatbot for a bank comes with several security challenges. We spent time considering these challenges: particularly the need for the protection of sensitive customer data, such as personal information and financial details as well as adhering to the compliance and privacy regulations requirements.

Mapping out chatbot and user needs

We worked through each use case in detail. Taking into account user needs and chatbot needs for each specific case: concentrating on goals, responsibilities, mindset and capabilities.

Sample Dialogue & Flowchart Design

Dialogue:

Part of our conversation design process was to spend time with the team going through the BNPPPF brand guidelines while adhering to their values of Responsibility, Transparency, Empathy and Simplicity.

We also looked at the tone of voice, examples of how different tones of voice worked and end-user expectations. Chatbot responses were then aligned with the tone of voice for all further working examples.

Flow design:

Designing flows with an interactive prototyping tool is a good way to progress a conversational ai project. We use Voiceflow for most of our projects. We were able to leverage the power of Voiceflow to enable rapid progress on conversation design to map realistic conversations and define complex processes.

Voiceflow enabled us to work on the conversation design quickly and collaborate with other stakeholders in the challenge.

"Production-ready conversational designs should be as reflective of the live experience as possible"

The Solution

Solution

Intelligent virtual agent proof of concept

From the finalised Voiceflow designs for each use case, we were able to create working prototypes for each specific user type: returning and new users.

The working prototype provided full functionality for each specific use case as a webchat interface. This was shared with the team at BNPPPF.

We were able to monitor chatbot POC usage by viewing the specific chat transcripts and iterating on the flows as needed.

The Results

Despite the obvious challenges of implementing a conversational AI solution for a large financial organisation and some difficulties caused by technology landscape changes, we were confident that we would be able to assist BNP Paribas with their long-term goals of improving customer experience and increasing efficiencies through the use of conversational AI technology.

Leveraging The Bot Forge's extensive expertise in conversational AI, we were able to transfer knowledge to BNPPPF in several ways:

  1. Workshops: The agency conducted onsite workshops and training sessions to educate the bank's team on the technology and best practices in the industry. This helped the bank to understand the capabilities of conversational AI and how it can be applied to their business.
  2. Bi-weekly meetings: The agency and the bank held regular meetings to discuss progress and address any questions or concerns. This helped to ensure that the bank's team was informed and on track with the implementation of the technology.
  3. Collaboration using modern tooling: Utilising Miro and Voiceflow software enabled us to collaborate on all areas of the challenge
  4. Conversational design: The agency created conversational designs based on agreed use cases which helped the bank's team to visualize how the technology can be used to improve customer engagement and streamline internal processes.
  5. Industry best practices: The agency shared its knowledge and experience of industry best practices, which helped the bank to understand how other companies in the industry were using conversational AI and how to apply these practices to their own organization.
IMG_5594

I am confident The Bot Forge will be able to give us digital solutions that improve the customer journey and help to reduce OPEX in the process.

Simon Jones (Head of Operations)

The results of the challenge were presented to all stakeholders and participants at the Serendip Showcase Event at the Science Centre in Birmingham.

Overall the feedback from the team at BNP Paribas Personal Finance was positive and challenge 3 was viewed as a success. Our expertise and knowledge allowed us to meet the demands of the challenge and have placed the team at BNP Paribas PF in a strong position to tackle their next phases of improving customer engagement and streamlining internal processes with conversational AI.

The Solution

Feedback

The Bot Forge were able to take us into the modern world with their experience and understanding of AI tools...very engaging and easy to work with. Flexible with time and always high energy. A pleasure to work with

Simon Jones
Head of Operations:  BNP Paribas Personal Finance

Need Help With Your Project?

If you'd like help achieving your chatbot, voice assistant or AI project objectives, please schedule a free consultation with one of our experts.