United Airlines has begun using Language Learning Models (LLMs) and artificial intelligence, such as ChatGPT, to inform customers about the status of their flights, which has resulted in a 6% boost in customer satisfaction.

Putting the AI in airlines

United Airlines
is exploring new waters with generative artificial intelligence initiatives used to enhance customer experience and process excellence (which is the term given to improving 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.

United Airlines Boeing 787-10 landing at TLV shutterstock_2416147463

Photo: Ronen Fefer | Shutterstock

Using United’s core data architectural backbone, including the United Data Hub and an AI and ML (Machine Learning) platform dubbed “Mars,” the airline has released a handful of models into production for employees and customers.

Speaking to CIO, the United Airlines Chief Information Officer, Jason Birnbaum, said this about the airline’s use of AI and LLMs:

“We worked hard to fine-tune this model to take operational feeds, notes from our operations teams, the crew, and all these different sources of data, and have AI take all this data and create a narrative that is more transparent, empathetic, decisive, and clear as we can be. As opposed to a canned message, we try to write a specific story about what’s going on with your flight. People hear the specifics, and they understand it and their blood pressure goes down. Our storytellers still look at the messages to make sure they’re within the realm of what we want to communicate but we’re getting much more comfortable with it.”

United utilizes ChatGPT for secure employee experimental use and an LLM for external users called “Every Flight Has a Story.” This flight-status service was released earlier this year and provides customers with faster, more transparent, context-rich information with efficiency. United Airlines has used the LLM to send out more than 100,000 push notifications and has identified 90 other use cases for the software.

Simple Flying has contacted United Airlines for a comment.

Behind the scenes

United’s “ “Every Flight Has a Story” LLM utilizes the “Mars” platform, which leverages Amazon Web Services (AWS) to automate digital notifications, streamline delay communications, and reduce the manual workload for human customer service agents. This has been achieved by automating many of the routine communications and personalizing responses at scale.

United Airlines 787 Christchurch Airport

Photo: Christchurch Airport

Francesca Vasquez, Vice President at AWS, admired the airline’s utilization of their platform for its innovative approach and emphasized the potential of generative AI in personalizing and automating communications. He said:

“United is just getting started. Historically, United storytellers had to manually edit templates, which took time. United realized that gen AI could automate most of these messages, freeing up their staff to focus on the more challenging delay issues — and an informed customer, for sure, is a happier customer.”

United is one of the earliest users of Amazon’s Sagemaker ML platform. According to AWS Vice President of Technology Mai-Lan Tomsen Bukovec, the airline’s use of these tools is going to become a game-changer.

In the future, United Airlines aims to use AI to help improve baggage handling, optimize flight routes, and improve predictive maintenance for aircraft.

Related

United Airlines Flight Canceled After Catering Truck Tips Over In Miami

The flight was already delayed by 18 hours before the incident occured.

Leave a Reply

Your email address will not be published. Required fields are marked *