A Survey on Session-based Recommender Systems

Recommender systems (RSs) have been playing an increasingly important role for informed consumption, services, and decision-making in the overloaded information era and digitized economy. In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs. Different from other RSs such as content-based RSs and collaborative filtering-based RSs that usually model long-term yet static user preferences, SBRSs aim to capture short-term but dynamic user preferences to provide more timely and accurate recommendations sensitive to the evolution of their session contexts. Although SBRSs have been intensively studied, neither unified problem statements for SBRSs nor in-depth elaboration of SBRS characteristics and challenges are available. It is also unclear to what extent SBRS challenges have been addressed and what the overall research landscape of SBRSs is. This comprehensive review of SBRSs addresses the above aspects by exploring in depth the SBRS entities (e.g., sessions), behaviours (e.g., users’ clicks on items), and their properties (e.g., session length). We propose a general problem statement of SBRSs, summarize the diversified data characteristics and challenges of SBRSs, and define a taxonomy to categorize the representative SBRS research. Finally, we discuss new research opportunities in this exciting and vibrant area.

Theoretical Framework for Design for Dynamic User Preferences

A key assumption of new product development is that user requirements and related preferences do not vary on time scales of the process length. However, prior work has identified cases in which user preferences for product attributes can vary with time. This study proposes a method, Design for Dynamic User Preferences, which adapts reinforcement learning (RL) algorithms for designing physical systems whose functionality changes with user feedback. An illustrative case comprised of the design of a variable stiffness prosthetic ankle is presented to evaluate the potential usefulness of the framework. Lifetime user satisfaction for static and dynamic design strategies are compared over simulated user preferences under a number of conditions. Results suggest RL-based strategies outperform static strategies for cases with dynamic user preferences despite significantly less initial information. Within RL methods, upper-confidence bound policies led to higher user satisfaction on average. This study suggests that further investigation into RL-based design strategies is warranted for situations with possibly dynamic preferences.

About time

Purpose The purpose of this paper seeks to develop a motivation-based complementary framework for temporally dynamic user preferences to facilitate optimal timing in web personalisation. It also aims to highlight the benefits of considering user motivation when addressing issues in temporal dynamics. Design/methodology/approach Through theory, a complementary framework and propositions for motivation-based temporal dynamics for further testing are created. The framework is validated by feeding back findings, whereas some of the propositions are validated through an experiment. Findings The suggested framework distinguishes two ways (identifying/learning and shifting) of using a motive-based approach to temporal dynamics in web personalisation. The suggested outcomes include enhanced timing in matching current preferences and improved conversion. Validation measures predominantly support both the framework and the tested propositions. The theoretical basis for the approach paves a path towards refined psychological user models; however, currently on a complementary level. Research limitations/implications While the framework is validated through feeding back findings, and some of the propositions are validated through basic experimentation, further empirical testing is required. Practical implications A generalised approach for complementing personalisation procedures with motivation-based temporal dynamics is offered, with implications for both user modelling and preference matching. Originality/value This paper offers novel insights to web personalisation by considering the in-depth effects of user motivation.