LHV Bank uses AlphaBlues to automate customer support with Conversational AI

  • Modern design and UX for customers through Conversational AI.
  • Natural language queries’ resolution rate at 26%.
  • Intelligent Routing from Virtual Assistant to customer service agents.

1. Business Challenge

LHV Group (NASDAQ: LHV1T) is the largest domestic financial group and capital provider in Estonia that is currently holding 2 billion euros of Estonian assets. The company employs over 400 people and has more than 5000 investors. LHV Bank services are used by more than 200,000 customers. Pension funds managed by LHV have over 175,000 customers and are the second largest in Estonia by volume.

The company is one of the most innovative and fastest growing banks in the region and was looking for a new and efficient way to engage with their customers 24/7. The aim was to provide customers a well-designed user experience with focus on automation to enable the bank to manage its user growth in the most efficient manner.

2. Solution

To automate their customer service, LHV turned to AlphaBlues and its Conversational AI product. Together with AlphaBlues LHV created its own Virtual Customer Assistant (VCA) – Uku. AlphaBlues worked with the bank to integrate their customer service knowledge base with hundreds of topics and intents into the VCA which was launched throughout the bank’s website.

Uku was trained on the AlphaBlues product to increase its relevancy and accuracy and to allow for more self-service by the bank’s customers. The VCA was given a friendly persona and it was taught to understand free text and natural language so as to be able to help people with the wide variety of questions they might have. Emphasis was placed on the following attributes:

2.1. User Experience

The VCA was embedded into a customized chat window with sleek design resembling the brand of the bank. More specifically we included a host of custom design attributes that make the VCA easier to use for the customer and also reflect the brand imagery of the Bank.

2.2. Handover from VCA to customer service agents

An integral part of AlphaAI (product for building VCAs) and AlphaChat (live chat product for agents) is the handover of the VCA conversation to LHV’s customer service agents. In this case we used the organizational structure and current workflows to be reflected in the VCA and its intelligent routing. Namely the features used by the agents were:

  • Custom groups queues by business branch and by language within each branch to reflect which divisions of the bank deal with which kind of tickets.
  • Automatic transcripts and chats with agents get sent to email.
  • Language based routing across 3 different languages to channel chats to agents that speak the specific language.
  • Auto-close of inactive chats for agents to not waste time on pinging customers who might be unresponsive.
  • Archive filtering, administrative view and operational logs for system monitoring.

When agents are unavailable (off-hours or busy) then the VCA triggers a special handover form. The customers can leave their name, email/phone number and message and this will be routed to the agents. Such a solution is helpful for the bank to leave the customers the opportunity to connect to agents whenever customers use the service.

3. Results

  • The VCA had tens of thousands of interactions with customers.
  • Carefully designed modern UX for enhanced customer interaction.
  • On average Uku successfully helped 26% of customers with their queries without the need to direct them to human support. This means that Uku 1) detected customer intent through natural language understanding; 2) provided an answer and 3) received confirmation from the customer that Uku’s answer was correct. Essentially the Conversational AI operated at a 26% level compared to humans.
  • LHV was able to measure the helpfulness rates on the individual intent level for a deeper understanding of their customer needs and ability to offer support.