Data Mining and Recommender Systems

Dear Colleagues,

Focus:

This Special Issue will spotlight the synergies between advanced data-mining techniques and next-generation recommender-system research. Emphasis will be placed on (i) novel mining methods that address the scale, heterogeneity, and dynamics of modern interaction data, and (ii) recommender architectures that translate mined patterns into actionable, trustworthy, and fair recommendations.

Scope:

This issue welcomes original contributions that span—but are not limited to—the following domains:

• Deep learning and graph-mining approaches for collaborative filtering, content-based, and hybrid recommendation;
• Explainable, causal, and counterfactual mining for transparent recommendation;
• Privacy-preserving and federated mining in recommendation system;
• Real-time and streaming-data mining for dynamic recommendations;
• Cross-domain, cross-lingual, and multimodal data mining for recommendation diversity;
• Evaluation, benchmark, and reproducibility studies that integrate data-mining insights with recommendation metrics;
• Industrial case studies and open-source toolkits that bridge mining theory and deployment practice.

Purpose：

This Special Issue aims to consolidate cutting-edge research that positions recommendation systems as both consumers and producers of data-mining knowledge. By doing so, it seeks to

• Establish common methodological ground for researchers in data mining and recommendation systems;
• Accelerate the translation of mining innovations into scalable, interpretable, and responsible recommendation solutions;
• Provide a forward-looking agenda that identifies open challenges and emerging opportunities at the intersection of the two fields.

A Useful Supplement to the Existing Literature：

While numerous surveys and journals have treated data mining and recommendation systems in isolation, this issue is the first to curate integrative studies that explicitly exploit mining advances to rethink recommendation design and vice versa. Specifically, it supplements the existing literature by

• Bridging the terminological and experimental divide between the KDD and RecSys communities through unified frameworks and shared benchmarks;
• Highlighting under-explored yet critical topics—such as fairness, privacy, and explainability—that demand joint attention from both fields;
• Disseminating reproducible artifacts (datasets, code, and evaluation protocols) that extend static benchmarks like MovieLens and Amazon Reviews to dynamic, multimodal, and federated settings;
• Offering industrial perspectives that reveal how large-scale mining pipelines overcome real-world bottlenecks in latency, sparsity, and concept drift—insights rarely captured in purely academic venues.

Overall, this Special Issue will serve as a timely, one-stop reference that not only synthesizes the current state of the art but also charts a research roadmap for the next decade of data-driven recommendation.

Prof. Dr. Quanlong Guan
Prof. Dr. Lianxi Wang
Dr. Zhengyang Wu
Guest Editors

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 250 words) can be sent to the Editorial Office for assessment.

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. Electronics is an international peer-reviewed open access semimonthly 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 2400 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.

• multimodal learning
• deep learning for recommendation
• graph mining
• privacy-preserving recommendation
• fairness in recommendation
• recommendation system