Streamlining Customer Support for 3rd Largest Digital Bank in the World: Leveraging NLP to Boost Customer Satisfaction by 9%
Our machine learning agency was asked by the 3rd largest digital bank in the world to find a solution to their customer support requests classification issues. The main goal was to develop an automated system that would classify customer support requests into the respective categories, ultimately saving precious time for customer service representatives.
What we've done
1. Data mining & filtering
2. Developed a deep learning model that can classify customer support requests into their respective categories with 90% accuracy.
3. Utilized natural language processing (NLP) techniques to determine the sentiment of customer support requests.
4. Created a predictive model to ensure timely response to customer support requests.
5. CI/CD & Deployment
The company asked us to help
— Collect dialogue data
— Design a system for their dialogue engine
— Optimise their software performance
— Provide a guidance on the next steps for model improvement
Our machine learning agency successfully developed a deep learning model that can accurately classify customer support requests into their respective categories. Utilizing natural language processing and sentiment analysis, we also created a predictive model to ensure timely response to customer support requests. Ultimately, the success of our project has helped the world’s top 3 largest digital bank to improve their customer satisfaction by 9% and support requests processing time by more than 87%.