Using AI to Help Airlines Make the Most of Ancillary Income

Image title

AI helps airlines make the most of ancillary income.

Airports are seldom places you want to spend a lot of time in, but from the operators’ perspectives, they view your time as an opportunity to extract cash from you. Indeed, some estimates suggest shoppers are likely to splurge an incredible $125,000,000,000 USD on duty-free shopping by 2025.

With the rise of low-cost airlines, however, shops aren’t the only way you might be fleeced at the airport, and new research highlights how airlines could be using AI to help them price services such as checked bags and seat reservations.

The researchers set out to counter the perception that such tools could be used to ring extra money out of passengers, however, and demonstrate how it could also deliver a cheaper and more personalized service to each passenger.

You may also like:  Streamlining Flight Operations With VR Aircraft Simulation

Cost Savings

Indeed, the researchers illustrate how smarter unbundling can create significant cost-saving opportunities as passengers are not required to pay for things they don’t need, whilst offering discounts to customers who may otherwise pass on certain extras can increase sales.

“Most airlines offer every customer the same price for a checked bag,” the researchers say. “However, not every customer has the same travel and budget needs. With AI, we can use information gathered while they shop to predict a price point at which they will be comfortable.”

The researchers believe a sweet spot can be reached using AI to track and assign a level of demand based upon each passenger’s unique flight preferences. These models take into account a range of factors, including the destination and origin of the flight, the time of travel and the duration of the trip.

For instance, if the trip is only a few days, there may be little incentive to pay for a checked bag, but if it can be discounted such that the convenience outweighs the cost, then it could encourage a sale.

Put to the Test

The system was put to the test with a European airline over a six-month period that involved both data gathering and testing. Passengers were required to log on to a pricing page before a number of them were offered discounts on various ancillary services.

“We started by offering the AI-modeled discounts to 5% of the customers who logged in,” the researchers say. “The airline then allowed us to adjust this percentage, as well as to experiment with various AI techniques used in our models, to obtain a robust data set.”

The results began to materialize almost straight away, with a rise in ancillary sales conversions alongside increased revenue per customer.

“Because of the unique nature of personalized pricing, we built a high level of equity and privacy into our models,” the authors continue. “There is a maximum price not to be exceeded, and we do not track customer demographics information like income, race, gender, etc., nor do we track a single customer during multiple visits to a sale site. Each repeat visit is viewed as a separate customer.”

The study was able to produce a boost in sales conversion and revenue per offer of 17% and 25% respectively, with AI allowing the company to move away from thinking of the average customer and more towards a personalized world of individual passengers.

“In recent years, the airline industry has felt that it has been losing touch with its customer base,” the authors conclude. “The industry is eager to find new ways to meet customer needs and to retain customer loyalty.”

Further Reading

Digital Transformation Use Case: Rome Airport

A Twitter Sentiment Analysis Pipeline for U.S. Airlines

This UrIoTNews article is syndicated fromDzone