Germany’s long distance rail network registers an all-time high demand for fast and comfortable train journeys. As capacity resources are limited, this calls for easy identification of trains and corridors with critical demand levels to avoid overcrowded trains and guarantee a save ride.
For that purpose, in short time and limited budget the software tool Peak Spotting was developed. It allows yield and capacity managers to identify potential bottlenecks based on passenger Ioad predictions and provides actionable information to several teams through data exploration and collaboration features. A machine learning module helps to identify critical trains and automated information transfer to production systems reduces manual work while increasing information quality directly for the customers of Deutsche Bahn.
In this talk, we present the design case study and share our lessons learnt in enabling innovation in a complex corporate setting. We will discuss the design and development process of the tool from ideation, data and concept exploration over design and implementation to usage tracking and iterative refinement. As the tool has proven its case and is under continuous development, we will also talk about its newest features and the roadmap ahead.
Of particular interest is the role of automation and analytics tools in digital transformation: how can we facilitate the transition from manual work and implicit knowledge to higher level tasks, supported by algorithms and visual analytics tools?
Mathias Richter, Senior Referent Digitale Transformation, DB Fernverkehr
Christian Laesser, Freelance Interaction Designer & Data Visualization Designer, Deutsche Bahn AG
Stephan Thiel, Co-Founder & Managing Director, Studio NAND