A systematic literature review of sparsity issues in recommender systems

Idrissi, Nouhaila; Zellou, Ahmed

doi:10.1007/s13278-020-0626-2

Cited by 78 publications

(44 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the present research, SLR was used as through a "protocol", it is possible to define a specific objective of investigation, to describe literature review sources, and select primary studies. Definitely, a protocol for a systematic review describes the rationale for the review, the objectives, and the methods that will be used to locate, select, and critically appraise studies, and to collect and analyze data from the included studies [23]. Although, SLR does not represent a scientific innovation, it is valuable since in a single document, it provides a complete, exhaustive summary of previous works produced on a specific topic [24].…”

Section: Introductionmentioning

confidence: 99%

Smart Manufacturing Systems and Applied Industrial Technologies for a Sustainable Industry: A Systematic Literature Review

et al. 2020

View full text Add to dashboard Cite

Smart manufacturing is considered as a new paradigm that makes work smarter and more connected, bringing speed and flexibility through the introduction of digital innovation. Today, digital innovation is closely linked to the “sustainability” of companies. Digital innovation and sustainability are two inseparable principles that are based on the concept of circular economy. Digital innovation enables a circular economy model, promoting the use of solutions like digital platforms, smart devices, and artificial intelligence that help to optimize resources. Thus, the purpose of the research is to present a systematic literature review on what enabling technologies can promote new circular business models. A total of 31 articles were included in the study. Our results showed that realization of the circular economy involved two main changes: (i) managerial changes and (ii) legislative changes. Furthermore, the creation of the circular economy can certainly be facilitated by innovation, especially through the introduction of new technologies and through the introduction of digital innovations.

show abstract

Section: Introductionmentioning

confidence: 99%

Smart Manufacturing Systems and Applied Industrial Technologies for a Sustainable Industry: A Systematic Literature Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This later can also be resulted from the fact that the similarity of two users is given by comparing their ratings for the same items, and users cannot be similar if they did not rate exactly the same items, even if those items are similar. Furthermore, as the majority of users assess only a small proportion of the available items [22], sparsity is a common issue for most recommendation systems [12].…”

Section: Related Workmentioning

confidence: 99%

“…RegSVD calculates the vectors p i and q j , iteratively, where the start values are calculated using equations (12) and (13). Then, the iterative regularization algorithm [23] is implemented as follows : e ij = r ij −r ij (15)…”

Section: Regsvdmentioning

confidence: 99%

“…The majority of these algorithms use the matrix R : users × items, containing stored evaluations [3]. Given that the ratings are not available for all tuples (user, item), the matrix R suffers from data sparseness (the majority of the values are missing) [12]. In order to predict the missing ratings, the proposed algorithms are based on the partial matrix factorization [12].…”

Section: Introductionmentioning

confidence: 99%

“…Given that the ratings are not available for all tuples (user, item), the matrix R suffers from data sparseness (the majority of the values are missing) [12]. In order to predict the missing ratings, the proposed algorithms are based on the partial matrix factorization [12]. Given the huge number of items to recommend and the number of users on one hand, and the small number of known user − item ratings on the other hand, the problem with these solutions is the data sparseness.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Like-tasted user groups to predict ratings in recommender systems

Jaffali

Jamoussi

Smaïli

et al. 2020

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Recommendation Systems have gained the intention of many researchers due to the growth of the business of personalizing, sorting and suggesting products to customers. Most of rating prediction in recommendation systems are based on customer preferences or on the historical behavior of similar customers. The similarity between customers is generally measured by the number of times customers liked or disliked the same item. Given the huge number and the variety of items, many customers cannot be considered as similar, as they did not evaluate the same items, even if they have similar tastes. This paper presents a new method of rating prediction in recommendation systems. The proposed method starts by identifying the taste directions or the interest centers based on the users' demographic information combined with their previous evaluations. Thus, it uses the Principal Component Analysis (PCA) to retrieve the major taste orientations. According to these orientations, user groups are created. Then, for each group, it generates a prediction model, that will be used to predict unknown rates of users within the corresponding group. In order to assess the accuracy of the proposed method, we compare its

show abstract

A Comparative Analysis of State-of-the-Art Recommendation Techniques in the Movie Domain

Valeriani

Sansonetti

Micarelli

2020

Computational Science and Its Applications – ICCSA 2020

View full text Add to dashboard Cite

Recommender systems (RSs) represent one of the manifold applications in which Machine Learning can unfold its potential. Nowadays, most of the major online sites selling products and services provide users with RSs that can assist them in their online experience. In recent years, therefore, we have witnessed an impressive series of proposals for novel recommendation techniques that claim to ensure significative improvements compared to classic techniques. In this work, we analyze some of them from a theoretical and experimental point of view and verify whether they can deliver tangible real improvements in terms of performance. Among others, we have experimented with traditional model-based and memory-based collaborative filtering, up to the most recent recommendation techniques based on deep learning. We have chosen the movie domain as an application scenario, and a version of the classic MovieLens as a dataset for training and testing our models.

show abstract

A systematic literature review of sparsity issues in recommender systems

Cited by 78 publications

References 64 publications

Smart Manufacturing Systems and Applied Industrial Technologies for a Sustainable Industry: A Systematic Literature Review

Smart Manufacturing Systems and Applied Industrial Technologies for a Sustainable Industry: A Systematic Literature Review

Like-tasted user groups to predict ratings in recommender systems

A Comparative Analysis of State-of-the-Art Recommendation Techniques in the Movie Domain

Contact Info

Product

Resources

About