A Hybrid of Sequential Rules and Collaborative Filtering for Product Recommendation

Cao

et al. 2019

Preprint

Session-based recommender systems (SBRS) are an emerging topic in the recommendation domain and have attracted much attention from both academia and industry in recent years. Most of existing works only work on modelling the general item-level dependency for recommendation tasks. However, there are many more other challenges at different levels, e.g., item feature level and session level, and from various perspectives, e.g., item heterogeneity and intra-and inter-item feature coupling relations, associated with SBRS. In this paper, we provide a systematic and comprehensive review on SBRS and create a hierarchical and in-depth understanding of a variety of challenges in SBRS. To be specific, we first illustrate the value and significance of SBRS, followed by a hierarchical framework to categorize the related research issues and methods of SBRS and to reveal its intrinsic challenges and complexities. Further, a summary together with a detailed introduction of the research progress is provided. Lastly, we share some prospects in this research area.

Section: Sequential Pattern-based Approachesmentioning

confidence: 99%

A Survey on Session-based Recommender Systems

Cao

et al. 2019

Preprint

Journal of Information Science

“…The hybrid approaches are based on using a combination of content-based and CF methods to improve the accuracy of the recommendation [8]. They are developed to use the advantages and overcome the disadvantages of different filtering approaches [17, 19, 37–39].…”

Section: Literature Reviewmentioning

confidence: 99%

A hybrid recommender system for the mining of consumer preferences from their reviews

Cheng

Lin

2019

Product review sites are widespread on the Internet and are rapidly gaining in popularity among consumers. This already large volume of user-generated content is dramatically growing every day, making it hard for consumers to filter out the worthwhile information which appears on the various review sites. There commendation system plays a significant role in solving the problem of information overload. This study proposes a framework which integrates a collaborative filtering approach and an opinion mining technique for movie recommendation. Within the proposed framework, sentiment analysis is first applied to the users’ reviews to detect consumer opinions about the movie they have watched and to explore the individual’s preference profile. Traditional recommendation models are overly dependent on preference ratings and often suffer from the problem of ‘data sparsity’. Experimental results obtained from real online reviews show that our proposed method is effective in dealing with insufficient data and is more accurate and efficient than existing traditional methods.

“…Most existing research on automated recommender systems focuses on developing algorithms that predict user preferences with minimal error, often employing item-or user-90 / Journal of Marketing, September 2012 based collaborative filtering techniques (e.g., Li et al 2007) or hybrid filtering methods (e.g., Liu, Lai, and Lee 2009). In addition to the contributions of information systems scholars (e.g., Koren 2009), marketing scholars have extended the discussion, such as with Ansari, Essegaier, and Kohli's (2000) Bayesian preference model and Ying, Feinberg, and Wedel's (2006) model that accounts for the latent processes underlying ratings.…”

Section: Research On Automated Recommenders For Individual Consumersmentioning

confidence: 99%

Can Automated Group Recommender Systems Help Consumers Make Better Choices?

Hennig‐Thurau

Marchand

Marx

2012

Journal of Marketing

Because hedonic products consist predominantly of experience attributes, often with many available alternatives, choosing the "right" one is a demanding task for consumers. Decision making becomes even more difficult when a group, instead of an individual consumer, will consume the product, as is regularly the case for hedonic offerings such as movies, opera performances, and wine. Noting the prevalence of automated recommender systems as decision aids, the authors investigate the power of group recommender systems that consider the preferences of all group members. The authors develop a conceptual framework of the effects of group recommenders and empirically examine these effects through two choice experiments. They find that automated group recommenders offer more valuable information than single recommenders when the choice agent must consume the recommended alternative. However, when agents choose freely among alternatives, the group's social relationship quality determines whether group recommenders actually create higher group value. Finally, group recommenders outperform decision making without automated recommendations if the agent's intention to use the systems is high. A decision tree model of recommender usage offers guidance to hedonic product managers.89 † Significant (p < .05) for two standard deviations. † † Significant (p < .05) for one and two standard deviations. Notes: n.s. = not significant. SRQ = social relationship quality, IN = intention toward recommender usage. The t-values are equal for slopes at group recommendation system and single/no recommendation system because these are dichotomous and thus SD-independent variables.