This paper presents ISeller an industry-strength recommendation system for online shopping platforms. The system supports several recommendation paradigms like collaborative, content-based and knowledge-based filtering as well as one-shot and conversational interaction modes. A generic user modelling component allows different forms of hybrid reasoning strategies as well as enables the system to support a process-oriented way of interactive selling in various product domains. This application paper contributes a comprehensive scenario for interactive selling on commercial platforms and thus motivates central user modelling services for recommendation systems.