The Impact of Search and Recommendation Systems on Sales in Electronic Commerce

Hinz, Oliver; Eckert, Jochen

doi:10.1007/s12599-010-0092-x

Cited by 58 publications

(38 citation statements)

References 29 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies that suggest recommenders might help increase sales diversity include Hinz and Eckert (2010);Oestreicher-Singer and Sundararajan (2012);Zhou et al (2010). In contrast, Fleder and Hosanagar (2009) use simulations to show that CFs are more likely to recommend items that have been viewed or purchased often, thereby reducing sales diversity.…”

Section: Prior Workmentioning

confidence: 99%

How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment

Lee

Hosanagar

2017

SSRN Journal

View full text Add to dashboard Cite

We investigate the impact of collaborative filtering recommender algorithms (e.g., Amazon's "Customers who bought this item also bought") commonly used in e-commerce on sales diversity. We use data from a randomized field experiment run on a top retailer in North America across 82,290 SKUs and 1,138,238 users. We report four main findings. First, we demonstrate across a wide range of product categories that the use of traditional collaborative filters (or CFs) is associated with a decrease in sales diversity relative to a world without product recommendations. Further, the design of the CF matters. CFs based on purchase data are associated with a greater effect size than those based on product views. Second, the decrease in aggregate sales diversity may not always be accompanied by a corresponding decrease in individual-level consumption diversity. In fact, it is even possible for individual consumption diversity to increase while aggregate sales diversity decreases. Third, co-purchase network analysis shows that recommenders can help individuals explore new products but similar users end up exploring the same kinds of products resulting in the concentration bias at the aggregate level. Fourth and finally, there is a difference between absolute and relative impact on niche items. Specifically, absolute sales and views for niche items in fact increase, but their gains are smaller compared to the gains in views and sales for popular items. Thus, while niche items gain in absolute terms, they lose out in terms of market shares. AbstractWe investigate the impact of collaborative filtering recommender algorithms (e.g., Amazon's "Customers who bought this item also bought") commonly used in e-commerce on sales diversity.We use data from a randomized field experiment run on a top retailer in North America across 82,290 SKUs and 1,138,238 users. We report four main findings. First, we demonstrate across a wide range of product categories that the use of traditional collaborative filters (or CFs) is associated with a decrease in sales diversity relative to a world without product recommendations.Further, the design of the CF matters. CFs based on purchase data are associated with a greater effect size than those based on product views. Second, the decrease in aggregate sales diversity may not always be accompanied by a corresponding decrease in individual-level consumption diversity. In fact, it is even possible for individual consumption diversity to increase while aggregate sales diversity decreases. Third, co-purchase network analysis shows that recommenders can help individuals explore new products but similar users end up exploring the same kinds of products resulting in the concentration bias at the aggregate level. Fourth and finally, there is a difference between absolute and relative impact on niche items. Specifically, absolute sales and views for niche items in fact increase, but their gains are smaller compared to the gains in views and sales for popular items. Thus, while niche items gain in absolut...

show abstract

Section: Prior Workmentioning

confidence: 99%

How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment

Lee

Hosanagar

2017

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…Given the potential they have to reduce the amount of effort demanded to make a decision and to increase decision accuracy, the use of recommendation agents can also impact e-vendors' strategies and revenues (Hinz and Eckert, 2010;Oestreicher-Singer and Sundararajan, 2010). Nevertheless the complexity of the variables that interfere on the way between the recommendation process and the users responses calls for new research capable of unveil some of these issues.…”

Section: Bothering Consumers: When Recommendation Agents Don'tmentioning

confidence: 99%

Incomodando consumidores: quando agentes de recomendação não facilitam a nossa vida realmente

Verruck

Nique

2017

BASE

View full text Add to dashboard Cite

Este é um artigo de acesso aberto, licenciado por Creative Commons Atribuição 4.0 Internacional (CC BY 4.0), sendo permitidas reprodução, adaptação e distribuição desde que o autor e a fonte originais sejam creditados. ABSTRACTIntelligent systems have been used in different types of websites with the intention of creating personalized messages and understanding consumers' needs more deeply. They are supposed to facilitate the decision-making process, make internet browsing easier and give users a sense of social feeling and personalization. So far, research in the field has focused attention on the positive aspects of using these systems. Little effort has been made, however, to try to recognize and correct situations in which they do not perform so well. This work is the result of an exploratory research destined to understand the broadness of the concept of failure in personalized environments as well as its antecedents and consequents. Based on the critical incident technique, we collected the opinion of 86 subjects in a multicultural environment and used their responses to elaborate a comprehensive framework of recommendation failure considering the different motivations for Internet use.Keywords: personalization, online shopping, recommendation agents, recommendation failure. RESUMOSistemas inteligentes têm sido usados em diferentes tipos de websites com a intenção de criar mensagens personalizadas e de entender as necessidades dos consumidores com mais profundidade. Eles supostamente facilitam o processo de tomada de decisão, tornam a navegação mais fácil e dão aos usuários uma sensação de trato social e personalização. Até agora, a pesquisa na área tem focado nos aspectos positivos de usar tais sistemas. Pouco esforço tem sido feito, entretanto, para tentar reconhecer e corrigir situações nas quais eles não apresentam um bom desempenho. Este trabalho é o resultado de uma pesquisa exploratória destinada a entender a amplitude do conceito de falha em ambientes personalizados, assim como seus antecedentes e consequentes. Baseados na técnica do incidente crítico, coletamos a opinião de 86 participantes em um ambiente multicultural e usamos suas respostas para elaborar um framework abrangente para a falha em recomendação, considerando as diferentes motivações para o uso da internet.Palavras-chave: personalização, compra on-line, agentes de recomendação, falha na recomendação.

show abstract

“…Some literature notes that good sales of e-commerce merchandise combined with network reviews and rankings will receive more benign evaluations and better sales results [3]. Another article indicates that ranking, as a form of non-personalized advertising, when used in conjunction with product deployment can result in significant sales of the targeted product by a large number of consumers [4]. The article Collaborative Filtering with Ordinal Scale-based Implicit Ratings for Mobile Music Recommendation discusses that on the intelligent mobile terminal, the explicit and implicit reviews play a key role in the sales of digital music [5].…”

Section: Literature Reviewmentioning

confidence: 99%

Matching Relation Between Consumer’s Psychology And Digital Goods Rankings

Chen

Wang

Liu

2015

Foundations of Computing and Decision Sciences

View full text Add to dashboard Cite

Abstract. The development of digital goods has profoundly changed the economic relationship and trading methods. Among all the digital goods recommendation information, ranking information is of prominent significance. The rankings impact consumers positively as they make decisions on buying digital products. We serve rankings and consumer psychologies as the object of this study, and will offer references and suggestions for the customization of the mobile terminal. Combining factor and cluster analysis, we subdivide the rankings into three groups first based on consumers' values and lifestyles: reputation ranking, consumption behavior ranking and purchase intention ranking. Then, we use a correspondence analysis method to conclude the matching relationship between different types of rankings and various consumption psychology groups.

show abstract

The Impact of Search and Recommendation Systems on Sales in Electronic Commerce

Cited by 58 publications

References 29 publications

How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment

How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment

Incomodando consumidores: quando agentes de recomendação não facilitam a nossa vida realmente

Matching Relation Between Consumer’s Psychology And Digital Goods Rankings

Contact Info

Product

Resources

About