Empirically Testing the Impact of Recommender Agents on Online Consumer Purchasing Behavior

Intelligent Product Recommendation Agents have been used for some time now by large, well known Internet businesses such as Amazon and Netflix. Unfortunately there is little research assessing the effectiveness of these systems in influencing online consumer behavior. Businesses that sell products via the Internet have little information to guide their decision making when deciding whether or not a capital investment in implementing such a system is warranted, and what the implementation of such a system will potentially do for their business. This research seeks to determine what impact recommender systems have on online consumer behavior so that managers and online business owners will have relevant data on which to base their decision of whether or not to implement such a system. This study develops a theoretical model which illustrates the impact that such recommender systems have on online consumer behavior. The model is tested using an online shopping simulation using a collaborative filtering based product recommendation agent. Particular attention is paid to the effects of the recommender agent on the consumer's behavior during the need recognition phase of Consumer Buyer Behavior Theory. The results of the study suggest that the theoretical model is sound and provides insight into the impact of recommender systems on online consumer behavior. Results suggest that such systems to affect online consumers and provide some valuable insights for online businesses considering implementing an intelligent product recommendation agent.