Advances in artificial intelligence and computing power are creating new opportunities for rail operators to forecast passenger demand and improve revenue from existing services. For Eric Nordling, Revenue Management Evangelist and General Manager of Expretio, the technology has reached a point where it can address challenges that were previously difficult to solve at scale.
Eric Nordling, Revenue Management Evangelist and General Manager of Expretio, said:For years we've understood the principles of revenue management, but the technology has finally caught up with the challenge. We can now analyse vastly more data, use hundreds of forecasting models and understand passenger demand with a level of accuracy that simply wasn't possible a decade or two ago.
The opportunity is particularly significant in rail, where a single train can serve hundreds of different journey combinations. Passengers board and alight at different stations, meaning each booking affects the capacity available for other journeys.
Eric Nordling said:One train can create more than 800 possible itineraries. Understanding demand for every one of those journeys is an enormous forecasting challenge.
Consider a service with strong demand between its starting point and an intermediate station, but more available seats further along the route. An operator needs to assess demand for each journey, rather than treating the train as a single block of capacity.
Selling a seat to someone travelling a short distance may prevent it being sold to a passenger travelling further. But reserving capacity for a potentially higher-value booking can also backfire if that passenger never books.
Revenue management systems use booking data, historical travel patterns and forecasting models to estimate how demand will develop across different journeys and departure times. These forecasts help operators make informed decisions about fares and the availability of seats, rather than relying solely on historical averages or manual adjustments.
Real-time information can add another layer of insight, but Nordling stresses that the objective is to anticipate demand, not merely react to what is happening on the network. The value comes from using data to predict what passengers are likely to do and making decisions before opportunities are lost.
Artificial intelligence and greater computing power can support this process by enabling more data to be analysed and more forecasting models to be applied. However, the technology still needs to address the right commercial questions; more information alone does not guarantee better results.
The potential benefits extend beyond maximising revenue. More accurate forecasts can help operators identify services with spare capacity, target discounts at quieter departures and understand where demand is likely to be strongest.
For passengers, this could mean more attractive fares when demand is lower. For operators, it offers the prospect of increasing ridership and revenue without necessarily adding more services.
As forecasting technology continues to develop, the opportunity is to turn increasingly sophisticated analysis into practical decisions about how seats are sold. For European rail operators, the prize is a better understanding of passenger demand – and a more effective use of the capacity already available.
Please share your perspectives on the Expretio LinkedIn profile page.
