Dear Colleagues,

Recommender systems (RS) serve as automated content-processing tools aiming to provide users with unknown, surprising, yet relevant objects without the necessity of explicitly querying for them. We are interested in the applications of RS in e-commerce. E-commerce systems usually provide users with a list or grid view as the output. Our focus is on the extension of e-commerce systems with an additional personalized spatial view, possibly with contour lines representing areas of higher preference.

For sequential access to web data/services, we assume together with [1] that the user’s preference is modeled for each attribute separately (each representing a relaxed value filter) and only at the end is combined/aggregated to overall preference. Therefore, we focus on the multivariate user’s preference, which is represented/approximated as a fuzzy aggregation of univariate function. Meanwhile, we expect the number of univariate functions to be equal to the number of attributes. On the other hand, we extend the aggregations instead of only the sum. This raises both theoretical and practical questions, e.g., characterizing the class of functions due to narrow representation and/or approximation; for each single user separately, given his/her behavior (a sample of visited objects with explicit (or implicit representation) overall preference score), the learning of each attribute preference separately and the learning of the aggregation with respect to some business-relevant metric must be designed.

Another aspect of our vision is visual recommendation. We have to distinguish between visualization because the domain is geometrical, e.g., a map [2], and visualization in considering the user interface, where the human ability to process visualized data can improve the recommendation process, e.g., see [3,4]. A comparison with general data visualization techniques is welcome, e.g., see [5–7]. In addition, see our work on contour line visualization in [7] and [8].

In such a context, there are still many challenges that must be faced in realizing RS with better business-relevant personalized recommendations. This Special Issue aims to promote new theories, techniques, methods, benchmarks, prototypes, experiments, and user studies with which to exploit visualization within a FLN-based recommendation framework. Potential topics include, but are not limited to, the following:

• Methods for estimating observed user preference with the FLN-class of functions (see [1]);
• Contour line visualization in higher dimensions;
• User studies;
• Online A/B testing in real production, especially in small-to-medium enterprises;
• Design for personalized visualization;
• Narrow multivariate functions representation/approximation by univariate functions and general fuzzy aggregation.

Prof. Dr. Peter Vojtas
Guest Editor

References

[1] Fagin R., Lotem A. and Naor M. Optimal aggregation algorithms for middleware, Comput. Syst. Sci. 2003, 66, 614–656.

[2] D. Weng, R. Chen, Z. Deng, F. Wu, J. Chen and Y. Wu. SRVis: Towards Better Spatial Integration in Ranking Visualization, IEEE Trans. Vis. Comput. Graph. 2019, 25, 459–469.

[3] C. He, D. Parra and K. Verbert. Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities, Expert Syst. Appl. 2016, 56, 9–27.

[4] S. Pajer, M. Streit, T. Torsney-Weir, F. Spechtenhauser, T. Möller and H. Piringer. WeightLifter: Visual Weight Space Exploration for Multi-Criteria Decision Making, IEEE Trans. Vis. Comput. Graph. 2017, 23, 611–620.

[5] Y. Albo, J. Lanir, P. Bak and S. Rafaeli. Off the Radar: Comparative Evaluation of Radial Visualization Solutions for Composite Indicators, IEEE Trans. Vis. Comput. Graph., 2016, 22, 569–578.

[6] E. Dimara, A. Bezerianos and P. Dragicevic. Conceptual and Methodological Issues in Evaluating Multidimensional Visualizations for Decision Support, IEEE Trans. Vis. Comput. Graph., 2018, 24, 749–759.

[7] Kopecky M. and Vojtas P. Visual E-Commerce Values Filtering Framework with Spatial Database Metric, accepted for Comput. Sci. Inf. Syst.

[8] Kopecky M. and Vojtas P. (2019) Graphical E-Commerce Values Filtering Model in Spatial Database Framework. In: Welzer T. et al. (eds) New Trends in Databases and Information Systems. ADBIS 2019. Communications in Computer and Information Science, vol. 1064. Springer, Cham, pp 210–220.

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• recommender systems
• online business
• e-commerce
• personalized visualization
• neural networks