2024 Franz Edelman Award

2024 Edelman Competition (video, special issue, INFORMS Journal on Applied Analytics)

Pierre Pinson, Mikkel Bjørn, Simon Kristiansen, Claus B. Nielsen, Lasse Janerka, Jesper Skovgaard, Kristian Durhuus (2025) Data-Driven at Sea: Forecasting and Revenue Management at Molslinjen. INFORMS Journal on Applied Analytics 55(1):5-21. https://doi.org/10.1287/inte.2024.0177 (2024 Franz Edelman Award Winner) (Keywords: ferry operations, demand forecasting, revenue management, machine learning  (by XGBoost))

Molslinjen, one of the world’s largest operators of fast-moving catamaran ferries, based in Denmark, adopted a focus on digitalization to profoundly change its operations and business practices. Molslinjen partnered with Halfspace, a data, analytics, and artificial intelligence (AI) company based in Copenhagen, Denmark, to support that transition. Halfspace and Molslinjen jointly developed and deployed a successful forecasting and revenue management toolbox for the data-driven operation of ferries in Denmark since 2020. This has resulted in $2.6–3.2 million yearly savings (and a total of $5 million savings as of December 2023), a significant reduction in the number of delayed departures and average delays, and a 3% reduction in fuel costs and emissions. This toolbox relies on some of the latest advances in machine learning for forecasting and in analytics approaches to revenue management. The potential for generalizing our toolbox to the global ferry industry is significant, with an impact on both revenues and environmental, societal, and governance criteria.

Two steps as in the case on Holiday Retirement. The procedure is similar to the case on Zara in my machine learning course.

1. Demand forecasting by XGBoost in machine learning
2. Inventory control in equation (4) by the Newsvendor model