Promoting Cold-Start Items in Recommender Systems

Lü, Jinhu; Zhou, Tao; Zhang, Zi-Ke; Yang, Zimo; Liu, Chuang; Liu, Weimin

doi:10.1371/journal.pone.0113457

Cited by 28 publications

(18 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is useful to think about these results in terms of the underlying process of music discovery. Because music is an experience good, consumers rely on sampling (Peitz and Waelbroeck 2006), word-of-mouth recommendations (Susarla et al 2012, Lee et al 2015, or automated recommender systems (Liu et al 2014, Zhou et al 2016 for their choice of which new musical content to consume. Underlying all of them is the notion that music discovery incurs search costs, and each of the three cues for consumers reduces search costs for new music.…”

Section: Discussionmentioning

confidence: 99%

Video Killed the Radio Star? Online Music Videos and Recorded Music Sales

Kretschmer

Peukert

2020

Information Systems Research

View full text Add to dashboard Cite

We study how online video platforms affect the sales volume and sales distribution of recorded music. To do so, we study two events that removed and then partially restored access to online music videos for consumers in Germany. Because of a legal dispute, virtually all music videos were blocked from YouTube, which led to a decrease in record sales of about 5%–10%. When the dedicated platform Vevo entered a few years later, record sales increased again by a similar amount. This is effect can be attributed to user-generated content (fan videos and cover versions) as much as to official music videos. Record sales of newcomer artists and mainstream music benefit disproportionally. We discuss the implications for debates on the reform of compulsory licensing rules and copyright.

show abstract

Section: Discussionmentioning

confidence: 99%

Video Killed the Radio Star? Online Music Videos and Recorded Music Sales

Kretschmer

Peukert

2020

Information Systems Research

View full text Add to dashboard Cite

show abstract

“…The NHSM model considers three user rating factors—proximity, significance, and singularity (PSS)—and combines local context information on these ratings with the global preferences of user ratings to alleviate the cold-start problem [68]. However, NHSM only considers co-rated items in identifying relationships between users [44].…”

Section: Related Workmentioning

confidence: 99%

An improved memory-based collaborative filtering method based on the TOPSIS technique

et al. 2018

View full text Add to dashboard Cite

This paper describes an approach for improving the accuracy of memory-based collaborative filtering, based on the technique for order of preference by similarity to ideal solution (TOPSIS) method. Recommender systems are used to filter the huge amount of data available online based on user-defined preferences. Collaborative filtering (CF) is a commonly used recommendation approach that generates recommendations based on correlations among user preferences. Although several enhancements have increased the accuracy of memory-based CF through the development of improved similarity measures for finding successful neighbors, there has been less investigation into prediction score methods, in which rating/preference scores are assigned to items that have not yet been selected by a user. A TOPSIS solution for evaluating multiple alternatives based on more than one criterion is proposed as an alternative to prediction score methods for evaluating and ranking items based on the results from similar users. The recommendation accuracy of the proposed TOPSIS technique is evaluated by applying it to various common CF baseline methods, which are then used to analyze the MovieLens 100K and 1M benchmark datasets. The results show that CF based on the TOPSIS method is more accurate than baseline CF methods across a number of common evaluation metrics.

show abstract

“…When formulating AS problem from the view of ML, it can be abstracted in different models [8][9][10]. More specifically: S AT zilla * applies pair-wise performance prediction from random forest classifiers [5,6], L L AM A creates the multiclass classification model to attribute a problem instance with meta features to an algorithm class [11], I S AC aggregates the similar training instances as a subset via clustering or k-NN and find the best algorithm on set basis for a new problem instance [12,13].…”

Section: Introductionmentioning

confidence: 99%

When algorithm selection meets Bi-linear Learning to Rank: accuracy and inference time trade off with candidates expansion

Jing

Geißler

Shao

et al. 2020

Int J Data Sci Anal

View full text Add to dashboard Cite

Algorithm selection (AS) tasks are dedicated to find the optimal algorithm for an unseen problem instance. With the knowledge of problem instances’ meta-features and algorithms’ landmark performances, Machine Learning (ML) approaches are applied to solve AS problems. However, the standard training process of benchmark ML approaches in AS either needs to train the models specifically for every algorithm or relies on the sparse one-hot encoding as the algorithms’ representation. To escape these intermediate steps and form the mapping function directly, we borrow the learning to rank framework from Recommender System (RS) and embed the bi-linear factorization to model the algorithms’ performances in AS. This Bi-linear Learning to Rank (BLR) has proven to work with competence in some AS scenarios and thus is also proposed as a benchmark approach. Thinking from the evaluation perspective in the modern AS challenges, precisely predicting the performance is usually the measuring goal. Though approaches’ inference time also needs to be counted for the running time cost calculation, it’s always overlooked in the evaluation process. The multi-objective evaluation metric Adjusted Ratio of Root Ratios (A3R) is therefore advocated in this paper to balance the trade-off between the accuracy and inference time in AS. Concerning A3R, BLR outperforms other benchmarks when expanding the candidates range to TOP3. The better effect of this candidates expansion results from the cumulative optimum performance during the AS process. We take the further step in the experimentation to represent the advantage of such TOPK expansion, and illustrate that such expansion can be considered as the supplement for the convention of TOP1 selection during the evaluation process.

show abstract

Promoting Cold-Start Items in Recommender Systems

Cited by 28 publications

References 56 publications

Video Killed the Radio Star? Online Music Videos and Recorded Music Sales

Video Killed the Radio Star? Online Music Videos and Recorded Music Sales

An improved memory-based collaborative filtering method based on the TOPSIS technique

When algorithm selection meets Bi-linear Learning to Rank: accuracy and inference time trade off with candidates expansion

Contact Info

Product

Resources

About