Trainline has revealed details of how it is using predictive analytics to help rail passengers save money when buying tickets on its app through the roll-out of its Price Prediction tool.
This service uses big data to judge how the price of an advance ticket will increase in the days leading up to the passenger’s departure date, based on information gleaned from billions of passenger journeys.
According to Trainline, rail passengers can save an average of 49% on prices if they pay when they first search for the journey.
For example, an advanced single ticket for a trip from London Euston to Manchester Piccadilly costs £32 around 80 days before departure but rises to £87 two days before.
Jon Moore, chief product officer at Trainline, told Computer Weekly that Price Prediction is an example of the “consumer tech-orientated product innovation” needed to improve the overall travel experience for rail users.
To collect the data, the company has been logging every ticket search and the price of the ticket at the point of search since October 2016, Moore said.
“That has allowed us to understand the likelihood and the timing of when that ticket expires. What we’ve released is the first deep insight into rail tickets and we’re excited to be the leader in this,” he said.
“It’s a representation of a deep understanding of rail and it comes to fruition through a heavy investment on our part in data science and data engineering.”
Read more about predictive analytics
- Predictive analytics is a challenge to implement but can provide businesses with a better understanding of their customers.
- The difference between predictive analytics and business intelligence.
- Read our 10 steps to help you build the foundations of a successful predictive analytics programme.
This investment has seen the company take steps to build out its data science and engineering teams over the past 18 months, Moore added. It has also yielded data-led innovations, such as Trainline’s BusyBot service. The tool uses crowdsourced data to find the quietest parts of a specific train and help passengers locate seats.
“We see billions of searches go through our platform and we sell tens of millions of tickets every few days. That attracts a certain type of data scientist and data engineer because a lot of companies are talking about big data but, unfortunately for them, they don’t necessarily have it – we do, so that’s helped us to attract some of the best in the business,” said Moore.