-
-
Autor*innen: Tavakol, Maryam; Brefeld, Ulf
Titel: Factored MDPs for detecting the topic of user sessions
Aus: Association for Computing Machinery (Hrsg.): RecSys' 14: Proceedings of the 8th ACM Conference on Recommender systems, Foster City; CA: ACM, 2014 , S. 33-40
DOI: 10.1145/2645710.2645739
URL: https://www.kma.informatik.tu-darmstadt.de/fileadmin/user_upload/Group_KMA/kma_publications/recsy160-tavakolATS.pdf
Dokumenttyp: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Sprache: Englisch
Schlagwörter: Empfehlungssystem; Information Retrieval; Interesse; Nutzerverhalten; Prognose; Thema
Abstract: Recommender systems aim to capture interests of users to provide tailored recommendations. User interests are however often unique and depend on many unobservable factors including a user's mood and the local weather. We take a contextual session-based approach and propose a sequential framework using factored Markov decision processes (fMDPs) to detect the user's goal (the topic) of a session. We show that an independence assumption on the attributes of items leads to a set of independent models that can be optimised efficiently. Our approach results in interpretable topics that can be effectively turned into recommendations. Empirical results on a real world click log from a large e-commerce company exhibit highly accurate topic prediction rates of about 90%. Translating our approach into a topic-driven recommender system outperforms several baseline competitors. (DIPF/Orig.)
DIPF-Abteilung: Informationszentrum Bildung