The Demand Effects of Product Recommendation Networks: An Empirical Analysis of Network Diversity and Stability

Lin, Z. X.; Goh, Khim Yong; Heng, Cheng-Suang

doi:10.25300/misq/2017/41.2.04

Cited by 51 publications

(34 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is well documented that the demand effects of co-view and co-purchase recommendations differ (Lin et al, 2015). This may be because Purchase-based CFs are more likely to recommend complementary rather than substitute products (and vice-versa for View-based CFs) (Lin et al, 2015). Our study is based on a retailer's implementation of item-based CF.…”

Section: Prior Workmentioning

confidence: 99%

“…Even among item-based CFs, they can be based on product views ("People who viewed this also viewed") or purchases ("People who bought this also bought"). It is well documented that the demand effects of co-view and co-purchase recommendations differ (Lin et al, 2015). This may be because Purchase-based CFs are more likely to recommend complementary rather than substitute products (and vice-versa for View-based CFs) (Lin et al, 2015).…”

Section: Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

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

Lee

Hosanagar

2019

Information Systems Research

138

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.

show abstract

Section: Prior Workmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

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

Lee

Hosanagar

2019

Information Systems Research

138

View full text Add to dashboard Cite

show abstract

“…Carmi et al studied that the direction of product links is important as it directs consumers' attention and generates traffic to a product [5]. LIN et al examine product recommendation networks in e-commerce to investigate how the demand of a product is influenced by product network attributes in terms of network diversity and network stability [6].…”

Section: Related Workmentioning

confidence: 99%

A Product Similarity Method Based on Deep Confidence Network

Liu¹,

Yu²,

Cao³

et al. 2019

Proceedings of the 2019 International Conference on Modeling, Simulation and Big Data Analysis (MSBDA 2019)

View full text Add to dashboard Cite

To improve product recommendation network, this paper mainly proposes a product similarity calculation algorithm based on deep confidence network. A high-dimensional product is firstly constructed and then input into the DBN model to obtain low-dimensional product feature data. Founded on the low-dimensional product feature data, the similarity between products can be calculated by the cosine formula. Through the data experiment, it is found that as the output dimension of the low-dimensional product feature matrix decreases, the similarity of the product similarity matrix also decreases, which means that the information extracted from the original input matrix is refined, and the effective information of a product is increasing, which means that the information extracted from the original input matrix is refined, and the effective information of a product is increasing.

show abstract

“…A recommendation system is a computer-mediated system configured to form a large web of interconnected products to help consumers find a product that meets their requirements and/or encourage them to purchase additional products to achieve cross-selling [12], [18]. When the recommendation system is implemented, each product in this network is connected to a group of products that share similar attributes and the network position of each product, as determined by the number of its incoming and outgoing links, affects the overall product demand [19].…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Canalization or Increased Diffusion? An Empirical Analysis on the Impact of the Recommendation System in the Mobile App Market

Liu

Jozani

Choo³

2018

Proceedings of the 51st Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Online retailers have increasingly adopted product recommendation systems as an effective tool to improve product visibility and promote sales. This study examines the impact of the recommendation system in the popular Google Play mobile app store. By analyzing a 60-day panel dataset with 235,638 observations from 9,735 apps, we investigate how the characteristics of the recommended apps relative to those of the focal apps affect the adoption of mobile apps in this volatile market. Our results show that the relative strength of the recommended apps over the focal app plays a key role in influencing the outcome of recommendations. Moreover, the heterogeneity of the recommendations as represented by the diversity of the popularity of the recommended apps is positively associated with a more even distribution of revenue in the market. These findings provide insights for mobile app market operators to enhance the design of their recommendation systems.

show abstract

The Demand Effects of Product Recommendation Networks: An Empirical Analysis of Network Diversity and Stability

Cited by 51 publications

References 71 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

A Product Similarity Method Based on Deep Confidence Network

Canalization or Increased Diffusion? An Empirical Analysis on the Impact of the Recommendation System in the Mobile App Market

Contact Info

Product

Resources

About