Industry
Finance
Technology
Java 8, Renesis, Webhook, Spring Boot, Oracle Database, WSO2, Rest Services, API AI, UML, Keycloak, Facebook Messenger API
Timeline
7 months

The Client

One of the leading banking institutions in Europe.

The Challenge

This project we carried out for our client from the financial industry. Their internal customer service department struggled with a heavy workload and time-consuming processes. They researched the possibilities to optimize it. Monotonous and repetitive tasks were tiring for the employees and were causing dissatisfaction. The client’s customer service team was dealing with a large number of queries. Some of them were repetitive and hence easy to automate.

Furthermore, due to the financial environment, there were a number of very particular and strict regulations to comply with. As the financial industry is exposed to complex regulations, adhering to the requirements of law was critical.

The process bots became the solution. Their task was to automate routine processes and handle the repetitive tasks in a similar way as human workers do. As they help to do things faster and more accurately, the customer service team could, in turn, focus on more business priorities.

The Solution

The goal of every chatbot is to analyze the customer’s question, take the shortest road to the query, report it, and then escalate it to the right department. When needed, it can ask additional questions if any details are missing.

Before building the solution for our client, an analysis of the project were needed to be made. Focus was made on collecting information on internal processes and regulations. To be able to synchronize to the chatbot technology, it was required to select the business processes that were repetitive and easy to optimize.

During the analysis, we chose the area to improve and made sure it’s the right field to optimize – first of all, if the process is repetitive. Nevertheless, the bot had to learn a number of queries and additional related questions. The main goal of the bot implementation was to shorten the way of the query – to report it and escalate it to the right department keeping the deadlines. 

Another important aspect was to gather all of the details of the query, and ask supplementary questions if necessary. We set up a range of questions that need to be answered in order to forward the query to another department. We also created numerous scenarios for a bot to be able to answer as many questions as possible. The next step was to create the dialog trees for the personalized conversations. The bot was expected to be able to analyze the details provided by the client and ask additional questions if any of the details were missing. 

Once these steps were completed, the MVP of the bot was released for further testing. The bot’s performance was measured with an accuracy indicator, which can reach even up to 93%, so it is crucial it can respond to questions correctly. The bot is programmed in such a way it can be adjusted after the implementation, for instance, to support the sales process or present special offers. Additional features, such as small talk ability can be developed. The MVP phase was very helpful and allowed us to eliminate the inaccuracies, where some of them couldn’t be predicted. 

The team consisted of 2 Developers, a Business Analyst, and a Knowledge Engineer. The Analyst handled the mapping of internal processes in the organization. The Knowledge engineer built conversations. Together they were responsible for bot improvements. They performed testing, conversation analysis, fixed errors, and eliminated irrelevant replies. The UX designer accompanied the team to design a conversation window. 

The technology stack we used in the process included Java, Apache, Cassandra, and Spring Boot. At the time we have written the so-called entity extractor based on NLP, and right now there are available libraries on the market. 

The Effect

Chatbots enhanced the customer experience. Not only did they allow customers to have their queries answered after call center working hours but also supplied immediate assistance to quickly fix the customer’s problem. They shortened reaction time and increased availability to report the query outside office hours.

From the employees’ perspective, the elimination of simple and repetitive tasks helped them to save time and allowed to focus on more engaging and complex queries, or on self-development. It made their work more satisfying.  Programming bots were also an opportunity to present the offer and new products to the customers who are interested in particular services. This led to increase sales of new products.

Moreover, bots helped to delegate tasks that required finding additional information for the customer for instance a cost or a particular number.

See also

Let’s talk about your project

This website uses cookies to deliver the service. Find out more or close the message.