The tanker industry is an old industry with very strong traditions. This also means that there is a fair amount of conservatism in the industry and there is therefore ample opportunity to revolutionize the industry e.g. by incorporating advanced analytics into the daily workflow of the frontline units. Maersk Tankers is determined to continue to pioneer this area by a devoted focus on becoming a digital tanker company. There are many elements in this, and one crucial element is revisiting all commercial decision and attempt to make them more data driven – on all levels in the organization.
In this presentation Christian Schultz, Data Scientist at Maersk Tankers, will give a brief presentation of the existing forecasting techniques employed in Maersk Tankers. The forecasting is primarily done by an ensemble model consisting of Gaussian Processes, Elastic Nets and Support Vector Regression. Furthermore some of the interesting projects in the pipeline will be discussed, among others the effort to build an Automated Cargo Identification System and the Automatic Voyage Predictor Model based on highly detailed historical vessel positions from the global tanker fleet.
Christian Schultz has a PhD in astrophysics from Aarhus University. After graduation he has worked in Danske Bank developing property valuation models and as a data scientist in Maersk Tankers.