In maritime transportation, pilotage plays a crucial role in ensuring navigational safety. Marine pilots possess in-depth knowledge of local waters, currents and weather conditions, guiding ships safely through complex waterways. This expertise minimises risks such as collisions and groundings, thereby protecting both the ship and the environment, and promoting safe, efficient maritime traffic management. However, grounding accidents in pilotage waters can still lead to severe environmental, economic and operational damage, including oil spills, ecosystem harm and costly salvage efforts. Continuous improvements in pilotage are therefore vital to minimise these risks. In this study, with the combination of HFACS methodology and Apriori algorithm, factors contributing to grounding accidents in ships navigating with marine pilots and ship features are examined, and strong association rules among factors are achieved. The prominent factors discovered are ‘Ship–Marine Pilot Communication Problems’, ‘Inappropriate Passage Plan’, ‘Ineffective Usage of Bridge Equipment’, ‘Port Authority Resource Management’ and ‘Ineffective Teamwork’. Ship-marine pilot communication problems are the most prevalent factor in these derived rules which is appearing in 8 of 9 rules and exerting a substantial influence on the accidents. Inappropriate passage planning, identified in 6 rules, emerges as another significant and recurrent contributing factor. Based on the association rules, this study provides significant insights and actionable recommendations for stakeholders to prevent grounding accidents in marine pilot-assisted navigation.

Managing high-variant product portfolios effectively is a crucial competitive advantage in offering mass customized products on saturated markets. Association Rule Mining (ARM) is a field of data mining determining frequent itemsets from historic transactions and deriving patterns of conclusion. This paper introduces a new approach to transfer ARM to feature-based configuration e.g. in the German automotive industry. Combined, existing apriori product knowledge is used in constraints to effectively lowering runtime by reducing the number of candidate-sets through introduction of a Boolean satisfiability check. For an efficient implementation, three different Apriori algorithms are tested and benchmarked on a generic dataset for different parameters. Results show a significant improvement in using SAT-based pre-screening while efficiency of the implementation depends on the given example.