The chatbot is a combination of various machine learning models that handle different aspects of natural language understanding, processing, and evaluation.
“This innovative use of AI not only enhances Scotiabank’s chatbot but also demonstrates creative problem-solving in sustaining customer-facing AI solutions, making it a deserving contender for the Most Innovative Use of AI Award.” – Judges’ comment.
In the absence of out of the box solutions, the Scotiabank team came up with the concept of building auxiliary AI models to sustain the chatbot. There are four models that sustain the chatbot: Luigi, EVA, Wall-E, and Peach. There is also Yoshi, a topic modeling algorithm that helps Scotiabank identify new areas of improvement for the chatbot. By utilizing these models, the team tapped into a database of curated data, reducing manual labor by thousands of hours in maintaining the organization’s chatbot. This enabled the chatbot to rapidly enhance its performance after launch, resulting in improved call containment and customer satisfaction.
“Together, these models streamline the sustainment process, leading to improved call containment and customer satisfaction.” – Judges’ comment.
Scotiabank has presented four machine learning models and one algorithm that sustain and improve the chatbot solution. These models handle different aspects of natural language processing and evaluation and work together to provide a seamless customer experience. The judges agreed that this is a creative approach of using auxiliary AI that can help sustain customer facing chatbots.
