Recommender Systems
Buch in deiner Nähe kaufen
Beschreibung
5 empirical studies, explanatory framework and management tool. Dissertation LMU München.
How to identify the most relevant recommender systems?
Recommender systems, such as “customers who bought this item also bought…“, are omnipresent in the internet and play a vital role in the online consumer purchase decision. Single web pages normally offer many recommender systems in parallel. The vast variety of in-use decision making systems is driven by sheer technological possibility.
Space constraints emerge with a continuously increasing number of available recommender systems and are enforced by the smaller screen sizes on mobile devices. The crucial question becomes - how to implement only the most relevant recommender systems – yet the question still waits for a comprehensive answer.
This dissertation takes up the challenge. It turns away from the software engineer perspective of creating one-size-fits-all solutions and takes up the business perspective of managing choice instead. Questions addressed are: How relevant are available recommender systems to my customers? At what point in the purchase is each needed most? What should I deploy to serve my customers best?
Sophie Ahrens shows that recommender system relevance is influenced by the underlying technology, purchasing context, and user characteristics in decision making. She delivers a framework that matches recommender systems and customer needs to increase online sales. Her book starts with a thorough literature review on recommender system, world-of-mouth, and consumer behavior research. It then presents a typology to classify recommender systems. A conceptual framework is developed to explain recommender system relevance drawing on theories pertaining to technology acceptance, consumer behavior, interpersonal persuasion and information processing. Five empirical studies employing innovative designs and various
data sources test and support its explanatory power. Findings are conveyed into a management tool to guide the optimal choice of recommender systems in practice.
Autor*in
Sophie Ahrens
2006-2010 Promotion zum Dr. oec publ., Ludwig-Maximilians-Universität (LMU) München und wissenschaftliche Mitarbeiterin; Columbia Business School, New York. 2007-2009 Postgraduales Studium betriebswirtschaftliche Forschung, Master of Business Research, LMU München. 2005-2007 Master Studium Technologiemanagement, Center for Digital Economy and Management (CDTM) München. 2000-2006 Diplom Betriebswirtschaftslehre, LMU München und Università degli Studi di Firenze, Florenz. Seit 2005 nebenberuflich in der IT-, Medien- und VC-Branche tätig.
Themen in »Recommender Systems«
Internet Empfehlungssysteme recommender system recommender agent Word-of-mouth WOM E-Commerce LMU München