Empirical Analysis of the Business Value of Recommender Systems

Abstract

Online retailers are increasingly using information technologies to provide value added services to customers. Prominent examples of these services are online recommender systems and consumer feedback mechanisms that serve to reduce consumer search costs and uncertainty associated with the purchase of unfamiliar products. The central question we address is the business value of online recommender systems to online retailers. We develop a robust empirical method that incorporates indirect impact of recommendations on sales through retailer pricing, potential simultaneity between sales and recommendations, and a comprehensive measure of the strength of recommendations. Applying the model to a panel data set collected from two online retailers, we found that the strength of recommendations has a positive impact on sales. We also found empirical evidence for the reinforcing effect of sales on recommendations and for the positive impact of recommendations on prices. These results suggest that recommendations not only improve sales but also provide added flexibility to retailers to adjust their prices. A comparative analysis reveals that recommendations have a higher impact on sales than consumer feedback. Our study demonstrates the value provided by information technology to an online retailer and provides guidelines for integrating recommender systems into their overall marketing strategy.

Keywords: Recommender Systems, Digital Word of Mouth, Electronic Commerce, Collaborative Filtering, Experience Goods, System of Equations