Start Date

11-8-2016

Description

Existing research on recommender systems has mostly focused on developing algorithms to predict the degrees to which a consumer may like a product. Recommended products are usually presented based on their predicted ratings in descending order. Considering the cognitive process of online consumers, when users evaluate the recommended products in sequence, the descending order may not necessarily be a good solution to increase consumers' willingness to purchase. Drawing upon the evaluability perspective and the order effects theory, we formulate a scenario where each product has two attributes, one of which can be evaluated independently while the other is difficult to evaluate without comparison. Analysis shows that in two out of the three cases of the scenario, presenting the most recommended product in the second place will result in higher consumer willingness to pay. The findings provide a new angle for understanding the behavioral implications of using recommender systems in ecommerce.

Share

COinS
 
Aug 11th, 12:00 AM

Order Effects in Online Product Recommendation: A Scenario-based Analysis

Existing research on recommender systems has mostly focused on developing algorithms to predict the degrees to which a consumer may like a product. Recommended products are usually presented based on their predicted ratings in descending order. Considering the cognitive process of online consumers, when users evaluate the recommended products in sequence, the descending order may not necessarily be a good solution to increase consumers' willingness to purchase. Drawing upon the evaluability perspective and the order effects theory, we formulate a scenario where each product has two attributes, one of which can be evaluated independently while the other is difficult to evaluate without comparison. Analysis shows that in two out of the three cases of the scenario, presenting the most recommended product in the second place will result in higher consumer willingness to pay. The findings provide a new angle for understanding the behavioral implications of using recommender systems in ecommerce.