United Airlines began using language learning models (LLMs) and artificial intelligence, such as ChatGPT, to inform customers about their flight status, resulting in a 6% increase in customer satisfaction.
United Airlines is exploring new waters with its artificial intelligence initiatives used to enhance customer experience and process excellence (which is given to improve how a business creates and delivers value to its customers). The airline has deployed sophisticated AI models to provide better, more transparent and human-like communication about flight delays, cancellations and service disruptions.
Using United's core data architectural backbone, including the United Data Hub and an AI and ML (machine learning) platform called “Mars,” the airline released a handful of models for production for employees and customers.
Speaking to CIO, United Airlines' Chief Information Officer, Jason Birnbaum, had this to say about the airline's use of AI and LLM:
“We've worked hard to fine-tune this model to take operational feeds, notes from our operations team, crews and all these different sources of data, and let the AI take all this data and be more transparent, empathetic, deterministic, and we As clear as I can be. Unlike a canned message, we try to write a specific story about what's going on with your flight. People hear specifics, and they understand it, and their blood pressure drops. Our storytellers still see the messages as being part of what we want to communicate, but we're getting more comfortable with it.”
United uses ChatGPT for secure employee testing and an LLM called “Every Flight has a Story” for external users. This flight-status service was released earlier this year and efficiently provides customers with faster, more transparent, context-rich information. United Airlines used LLM to send more than 100,000 push notifications and identified 90 other use cases for the software.
United's “Every Flight Has a Story” LLM uses the “Mars” platform, which uses Amazon Web Services (AWS) to automate digital notifications, streamline delay communications, and reduce manual workloads for human customer service agents. It automates many routine communications. By and by personalizing feedback at scale.
Francesca Vasquez, vice president of AWS, praised the airlines' innovative approach to using their platform and emphasized the potential of generative AI in personalization and automated communications. He said:
“United are just getting started. Historically, United Storytellers had to edit templates manually, which took time. United realized that General AI could automate much of this messaging, freeing up their staff to focus on more challenging latency issues – and an informed customer is, for sure, a happy customer.”
United was one of the early adopters of Amazon's SageMaker ML platform. Airlines' use of these tools is going to be a game-changer, according to My-Lan Tomsen Bukovec, AWS vice president of technology.
In the future, United Airlines aims to use AI to improve baggage handling, optimize flight routes and improve predictive maintenance for aircraft.