UK: Inter-city operator LNER is rolling out a machine learning-based tool which helps its station staff predict train delays and adapt the support they provide to more closely meet passenger needs.
The digital tool takes previous train performance data and adds in factors such as the number of people travelling and weather conditions to highlight services which may encounter a delay.
It was developed by LNER’s in-house machine learning team and is available to its staff via their company mobile phone.
‘To be forewarned is to be forearmed’, said Machine Learning Product Lead Steven Lloyd on March 20. The tool ’highlights pinch points, enabling teams to be proactive in reducing the reason for delay’.
Trials at Peterborough and Newark Northgate stations reduced dwell times, and more than 450 potential delays were avoided.
‘The insight provided by the predictive delay tool allows us to plan more effectively, keeping our customers and our trains on the move’, said Ian Whittles, Station Delivery Manager at Peterborough.
