BOOMER — An algorithm for learning gradient boosted multi-label classification rules

Multi-label classification is concerned with the assignment of sets labels to individual data points. Due its diverse real-world applications, e.g., annotation text documents topics, it has become a well-established field machine learning research. Compared traditional classification, where classes are mutually exclusive, multi-label comes interesting challenges, most prominently requirement take dependencies between into account. In this work, we present modular and customizable implementation BOOMER – an algorithm for gradient boosted rules that can flexibly be adjusted different use cases requirements.