Recommendation Systems in Electronic Markets
Special issue of Electronic Markets; Deadline 1 Jun 2019
Electronic Markets – The International Journal on Networked Business
Call for Papers
“Recommendation Systems (RS) in Electronic Markets”
- Ravi S. Sharma, University of Canterbury Business School, firstname.lastname@example.org
- Eldon Li, California Polytechnic, San Luis, USA & Tongji University, Shanghai, China, email@example.com
- Aijaz A. Shaikh, University of Jyväskylä, Finland, firstname.lastname@example.org
This special issue focuses on the use of recommendations or suggestions from the marketplace in order to capture value. The business value of a recommendation or suggestion is that it helps e-businesses (including e-commerce) and social media platforms to uncover associations that are amongst large amounts of transactions data, for the purpose of providing personalized shopping suggestions and recommendations to consumers. A Recommendation Systems (RS), therefore, would be a significant opportunity for monetization providing a competitive advantage to firms in the electronic marketplace by helping with up- and cross-sales (Heimbach et al., 2015), reducing consumers’ costs for searches (Köhler et al., 2016) and other innovative forms of bundling digital products.
Development of state-of-the-art RS — defined as software agents that are widely utilized in online platforms to elicit users’ preferences and interests to generate product or service recommendations (Heimbach et al., 2015) — is becoming popular in the e-commerce industry for retrieving and recommending the most relevant information regarding items, services, and products for users (Khan et al., 2018). It is an intuitive step to overcome the information overload problem in electronic markets. Recently, Hsu et al (2018) reported after an extensive survey of the RS literature, a mapping of RS techniques with application domains with the potential of significant impact. However, the report did not provide specific frameworks, models, measures or use-cases for success.
For example, Business Insider reported in 2017 that over 80% of the Netflix business was generated from its RS and the remaining less than 20% was generated from searches. Netflix believes that it would lose US$1 billion or more, yearly, if not for personalized recommendation engine that maintains its subscribers. Google recently introduced an improved design and RS to the Home screen of its YouTube application, in order to entice viewers to continue to watch the videos, and to “…create the feeling that YouTube understands you.” Apple’s Watch List will recommend content and present accompanying marketing messages across their Apple TV devices, through a “…universal search and suggestion mechanism…” that delivers the content as quickly as possible. MightyTV is a meta-RS which allows consumers to swipe through a list of movies or shows across service-providers such as Netflix, Hulu, or HBO, and consequently suggests new shows that they should watch, based on profiles. In a value-added feature, known as “mash-up,” consumers can connect with friends for the RS algorithm to model what their tastes have in common, from shows to specific actors. However, while high-quality, personalized recommendations can benefit users, online businesses may violate laws if they collect too much user data or if they globalize its use.
It is therefore timely to consider state-of-the-art strategies, approaches, and case studies of RS that may be adopted in global electronic markets.
Central issues and themes
The topics may include, but are not limited to, the following:
- Frameworks and models for effective RS in the global, networked economy
- Mapping state-of-the-art RS techniques to characteristics of electronic markets
- The applications of RS in social-commerce, m-commerce, e-government, e-tourism, e-learning, and crowd-sourcing
- Global consumer and business perspectives on RS
- RS architecture for business value creation and capture
- Trends and directions of RS platforms, services, and applications
- Approaches to monetizing of effective RS
- Legal and ethical issues in aggregate user data protection (e.g., a differential privacy model, post General Data Protection Regulations)
- Benchmarking RS effectiveness with social media and networks
- Predictive and prescriptive analytics for RS
- Innovative use-cases of RS in next-generation electronic markets (ie. beyond mobile, social commerce)
- Business outcomes of RS in industry clusters
Electronic Markets covers diverse aspects of networked businesses and welcomes research from technological, organizational, societal, and/or political perspectives. We encourage contributions with a broad range of methodological approaches; hence conceptual and theory-development papers, empirical hypothesis testing, and case-based studies are all welcome. All papers should fit the scope of the Electronic Markets journal (for more information see http://www.electronicmarkets.org/about-em/scope/) and will undergo a double-blind, peer review process. If you would like to discuss any aspect of this special issue, please contact the guest editors.
Electronic Markets is a Social Science Citation Index (SSCI)-listed journal (IF 3.818 in 2017) and requires that all papers be original and not published or under review elsewhere. Papers must be submitted through our journal’s electronic submission system at http://elma.edmgr.com and conform to the Electronic Markets journal’s publication standards (see instructions and templates at http://www.electronicmarkets.org/authors). Please note that the preferred article length is approximately 8,000 words, excluding references.
Submission Deadline: June 1, 2019
References / Suggested Readings:
Hsu, P. Y., Lei, H. T., Huang, S. H., Liao, T. H., Lo, Y. C., & Lo, C. C. (2018). Effects of sentiment on recommendations in social network. Electronic Markets, 28(1), 1-10. [online]
Heimbach, I., Gottschlich, J., & Hinz, O. (2015). The value of user’s Facebook profile data for product recommendation generation. Electronic Markets, 25(2), 125-138.
J. Lu, D. Wu, M. Mao, W. Wang, & G. Zhang (2015). Recommender system application developments: a survey, Decision Support Systems, 74, 12–32.
Khan, Z. A., Chaudhary, N. I., & Zubair, S. (2018). Fractional stochastic gradient descent for recommender systems. Electronic Markets, (28) 1-11. [online]
Köhler, S., Wöhner, T., & Peters, R. (2016). The impact of consumer preferences on the accuracy of collaborative filtering recommender systems. Electronic Markets, 26(4), 369-379.